WorldWideScience

Sample records for regression variable selection

  1. Variable and subset selection in PLS regression

    DEFF Research Database (Denmark)

    Høskuldsson, Agnar

    2001-01-01

    The purpose of this paper is to present some useful methods for introductory analysis of variables and subsets in relation to PLS regression. We present here methods that are efficient in finding the appropriate variables or subset to use in the PLS regression. The general conclusion...... is that variable selection is important for successful analysis of chemometric data. An important aspect of the results presented is that lack of variable selection can spoil the PLS regression, and that cross-validation measures using a test set can show larger variation, when we use different subsets of X, than...

  2. Variable Selection for Regression Models of Percentile Flows

    Science.gov (United States)

    Fouad, G.

    2017-12-01

    Percentile flows describe the flow magnitude equaled or exceeded for a given percent of time, and are widely used in water resource management. However, these statistics are normally unavailable since most basins are ungauged. Percentile flows of ungauged basins are often predicted using regression models based on readily observable basin characteristics, such as mean elevation. The number of these independent variables is too large to evaluate all possible models. A subset of models is typically evaluated using automatic procedures, like stepwise regression. This ignores a large variety of methods from the field of feature (variable) selection and physical understanding of percentile flows. A study of 918 basins in the United States was conducted to compare an automatic regression procedure to the following variable selection methods: (1) principal component analysis, (2) correlation analysis, (3) random forests, (4) genetic programming, (5) Bayesian networks, and (6) physical understanding. The automatic regression procedure only performed better than principal component analysis. Poor performance of the regression procedure was due to a commonly used filter for multicollinearity, which rejected the strongest models because they had cross-correlated independent variables. Multicollinearity did not decrease model performance in validation because of a representative set of calibration basins. Variable selection methods based strictly on predictive power (numbers 2-5 from above) performed similarly, likely indicating a limit to the predictive power of the variables. Similar performance was also reached using variables selected based on physical understanding, a finding that substantiates recent calls to emphasize physical understanding in modeling for predictions in ungauged basins. The strongest variables highlighted the importance of geology and land cover, whereas widely used topographic variables were the weakest predictors. Variables suffered from a high

  3. Sparse Reduced-Rank Regression for Simultaneous Dimension Reduction and Variable Selection

    KAUST Repository

    Chen, Lisha

    2012-12-01

    The reduced-rank regression is an effective method in predicting multiple response variables from the same set of predictor variables. It reduces the number of model parameters and takes advantage of interrelations between the response variables and hence improves predictive accuracy. We propose to select relevant variables for reduced-rank regression by using a sparsity-inducing penalty. We apply a group-lasso type penalty that treats each row of the matrix of the regression coefficients as a group and show that this penalty satisfies certain desirable invariance properties. We develop two numerical algorithms to solve the penalized regression problem and establish the asymptotic consistency of the proposed method. In particular, the manifold structure of the reduced-rank regression coefficient matrix is considered and studied in our theoretical analysis. In our simulation study and real data analysis, the new method is compared with several existing variable selection methods for multivariate regression and exhibits competitive performance in prediction and variable selection. © 2012 American Statistical Association.

  4. Variable selection and model choice in geoadditive regression models.

    Science.gov (United States)

    Kneib, Thomas; Hothorn, Torsten; Tutz, Gerhard

    2009-06-01

    Model choice and variable selection are issues of major concern in practical regression analyses, arising in many biometric applications such as habitat suitability analyses, where the aim is to identify the influence of potentially many environmental conditions on certain species. We describe regression models for breeding bird communities that facilitate both model choice and variable selection, by a boosting algorithm that works within a class of geoadditive regression models comprising spatial effects, nonparametric effects of continuous covariates, interaction surfaces, and varying coefficients. The major modeling components are penalized splines and their bivariate tensor product extensions. All smooth model terms are represented as the sum of a parametric component and a smooth component with one degree of freedom to obtain a fair comparison between the model terms. A generic representation of the geoadditive model allows us to devise a general boosting algorithm that automatically performs model choice and variable selection.

  5. Variable selection in Logistic regression model with genetic algorithm.

    Science.gov (United States)

    Zhang, Zhongheng; Trevino, Victor; Hoseini, Sayed Shahabuddin; Belciug, Smaranda; Boopathi, Arumugam Manivanna; Zhang, Ping; Gorunescu, Florin; Subha, Velappan; Dai, Songshi

    2018-02-01

    Variable or feature selection is one of the most important steps in model specification. Especially in the case of medical-decision making, the direct use of a medical database, without a previous analysis and preprocessing step, is often counterproductive. In this way, the variable selection represents the method of choosing the most relevant attributes from the database in order to build a robust learning models and, thus, to improve the performance of the models used in the decision process. In biomedical research, the purpose of variable selection is to select clinically important and statistically significant variables, while excluding unrelated or noise variables. A variety of methods exist for variable selection, but none of them is without limitations. For example, the stepwise approach, which is highly used, adds the best variable in each cycle generally producing an acceptable set of variables. Nevertheless, it is limited by the fact that it commonly trapped in local optima. The best subset approach can systematically search the entire covariate pattern space, but the solution pool can be extremely large with tens to hundreds of variables, which is the case in nowadays clinical data. Genetic algorithms (GA) are heuristic optimization approaches and can be used for variable selection in multivariable regression models. This tutorial paper aims to provide a step-by-step approach to the use of GA in variable selection. The R code provided in the text can be extended and adapted to other data analysis needs.

  6. Exhaustive Search for Sparse Variable Selection in Linear Regression

    Science.gov (United States)

    Igarashi, Yasuhiko; Takenaka, Hikaru; Nakanishi-Ohno, Yoshinori; Uemura, Makoto; Ikeda, Shiro; Okada, Masato

    2018-04-01

    We propose a K-sparse exhaustive search (ES-K) method and a K-sparse approximate exhaustive search method (AES-K) for selecting variables in linear regression. With these methods, K-sparse combinations of variables are tested exhaustively assuming that the optimal combination of explanatory variables is K-sparse. By collecting the results of exhaustively computing ES-K, various approximate methods for selecting sparse variables can be summarized as density of states. With this density of states, we can compare different methods for selecting sparse variables such as relaxation and sampling. For large problems where the combinatorial explosion of explanatory variables is crucial, the AES-K method enables density of states to be effectively reconstructed by using the replica-exchange Monte Carlo method and the multiple histogram method. Applying the ES-K and AES-K methods to type Ia supernova data, we confirmed the conventional understanding in astronomy when an appropriate K is given beforehand. However, we found the difficulty to determine K from the data. Using virtual measurement and analysis, we argue that this is caused by data shortage.

  7. Sparse Reduced-Rank Regression for Simultaneous Dimension Reduction and Variable Selection

    KAUST Repository

    Chen, Lisha; Huang, Jianhua Z.

    2012-01-01

    and hence improves predictive accuracy. We propose to select relevant variables for reduced-rank regression by using a sparsity-inducing penalty. We apply a group-lasso type penalty that treats each row of the matrix of the regression coefficients as a group

  8. Penalized regression procedures for variable selection in the potential outcomes framework.

    Science.gov (United States)

    Ghosh, Debashis; Zhu, Yeying; Coffman, Donna L

    2015-05-10

    A recent topic of much interest in causal inference is model selection. In this article, we describe a framework in which to consider penalized regression approaches to variable selection for causal effects. The framework leads to a simple 'impute, then select' class of procedures that is agnostic to the type of imputation algorithm as well as penalized regression used. It also clarifies how model selection involves a multivariate regression model for causal inference problems and that these methods can be applied for identifying subgroups in which treatment effects are homogeneous. Analogies and links with the literature on machine learning methods, missing data, and imputation are drawn. A difference least absolute shrinkage and selection operator algorithm is defined, along with its multiple imputation analogs. The procedures are illustrated using a well-known right-heart catheterization dataset. Copyright © 2015 John Wiley & Sons, Ltd.

  9. Coupled variable selection for regression modeling of complex treatment patterns in a clinical cancer registry.

    Science.gov (United States)

    Schmidtmann, I; Elsäßer, A; Weinmann, A; Binder, H

    2014-12-30

    For determining a manageable set of covariates potentially influential with respect to a time-to-event endpoint, Cox proportional hazards models can be combined with variable selection techniques, such as stepwise forward selection or backward elimination based on p-values, or regularized regression techniques such as component-wise boosting. Cox regression models have also been adapted for dealing with more complex event patterns, for example, for competing risks settings with separate, cause-specific hazard models for each event type, or for determining the prognostic effect pattern of a variable over different landmark times, with one conditional survival model for each landmark. Motivated by a clinical cancer registry application, where complex event patterns have to be dealt with and variable selection is needed at the same time, we propose a general approach for linking variable selection between several Cox models. Specifically, we combine score statistics for each covariate across models by Fisher's method as a basis for variable selection. This principle is implemented for a stepwise forward selection approach as well as for a regularized regression technique. In an application to data from hepatocellular carcinoma patients, the coupled stepwise approach is seen to facilitate joint interpretation of the different cause-specific Cox models. In conditional survival models at landmark times, which address updates of prediction as time progresses and both treatment and other potential explanatory variables may change, the coupled regularized regression approach identifies potentially important, stably selected covariates together with their effect time pattern, despite having only a small number of events. These results highlight the promise of the proposed approach for coupling variable selection between Cox models, which is particularly relevant for modeling for clinical cancer registries with their complex event patterns. Copyright © 2014 John Wiley & Sons

  10. Two-step variable selection in quantile regression models

    Directory of Open Access Journals (Sweden)

    FAN Yali

    2015-06-01

    Full Text Available We propose a two-step variable selection procedure for high dimensional quantile regressions, in which the dimension of the covariates, pn is much larger than the sample size n. In the first step, we perform ℓ1 penalty, and we demonstrate that the first step penalized estimator with the LASSO penalty can reduce the model from an ultra-high dimensional to a model whose size has the same order as that of the true model, and the selected model can cover the true model. The second step excludes the remained irrelevant covariates by applying the adaptive LASSO penalty to the reduced model obtained from the first step. Under some regularity conditions, we show that our procedure enjoys the model selection consistency. We conduct a simulation study and a real data analysis to evaluate the finite sample performance of the proposed approach.

  11. Selecting minimum dataset soil variables using PLSR as a regressive multivariate method

    Science.gov (United States)

    Stellacci, Anna Maria; Armenise, Elena; Castellini, Mirko; Rossi, Roberta; Vitti, Carolina; Leogrande, Rita; De Benedetto, Daniela; Ferrara, Rossana M.; Vivaldi, Gaetano A.

    2017-04-01

    Long-term field experiments and science-based tools that characterize soil status (namely the soil quality indices, SQIs) assume a strategic role in assessing the effect of agronomic techniques and thus in improving soil management especially in marginal environments. Selecting key soil variables able to best represent soil status is a critical step for the calculation of SQIs. Current studies show the effectiveness of statistical methods for variable selection to extract relevant information deriving from multivariate datasets. Principal component analysis (PCA) has been mainly used, however supervised multivariate methods and regressive techniques are progressively being evaluated (Armenise et al., 2013; de Paul Obade et al., 2016; Pulido Moncada et al., 2014). The present study explores the effectiveness of partial least square regression (PLSR) in selecting critical soil variables, using a dataset comparing conventional tillage and sod-seeding on durum wheat. The results were compared to those obtained using PCA and stepwise discriminant analysis (SDA). The soil data derived from a long-term field experiment in Southern Italy. On samples collected in April 2015, the following set of variables was quantified: (i) chemical: total organic carbon and nitrogen (TOC and TN), alkali-extractable C (TEC and humic substances - HA-FA), water extractable N and organic C (WEN and WEOC), Olsen extractable P, exchangeable cations, pH and EC; (ii) physical: texture, dry bulk density (BD), macroporosity (Pmac), air capacity (AC), and relative field capacity (RFC); (iii) biological: carbon of the microbial biomass quantified with the fumigation-extraction method. PCA and SDA were previously applied to the multivariate dataset (Stellacci et al., 2016). PLSR was carried out on mean centered and variance scaled data of predictors (soil variables) and response (wheat yield) variables using the PLS procedure of SAS/STAT. In addition, variable importance for projection (VIP

  12. Purposeful selection of variables in logistic regression

    Directory of Open Access Journals (Sweden)

    Williams David Keith

    2008-12-01

    Full Text Available Abstract Background The main problem in many model-building situations is to choose from a large set of covariates those that should be included in the "best" model. A decision to keep a variable in the model might be based on the clinical or statistical significance. There are several variable selection algorithms in existence. Those methods are mechanical and as such carry some limitations. Hosmer and Lemeshow describe a purposeful selection of covariates within which an analyst makes a variable selection decision at each step of the modeling process. Methods In this paper we introduce an algorithm which automates that process. We conduct a simulation study to compare the performance of this algorithm with three well documented variable selection procedures in SAS PROC LOGISTIC: FORWARD, BACKWARD, and STEPWISE. Results We show that the advantage of this approach is when the analyst is interested in risk factor modeling and not just prediction. In addition to significant covariates, this variable selection procedure has the capability of retaining important confounding variables, resulting potentially in a slightly richer model. Application of the macro is further illustrated with the Hosmer and Lemeshow Worchester Heart Attack Study (WHAS data. Conclusion If an analyst is in need of an algorithm that will help guide the retention of significant covariates as well as confounding ones they should consider this macro as an alternative tool.

  13. Penalized variable selection in competing risks regression.

    Science.gov (United States)

    Fu, Zhixuan; Parikh, Chirag R; Zhou, Bingqing

    2017-07-01

    Penalized variable selection methods have been extensively studied for standard time-to-event data. Such methods cannot be directly applied when subjects are at risk of multiple mutually exclusive events, known as competing risks. The proportional subdistribution hazard (PSH) model proposed by Fine and Gray (J Am Stat Assoc 94:496-509, 1999) has become a popular semi-parametric model for time-to-event data with competing risks. It allows for direct assessment of covariate effects on the cumulative incidence function. In this paper, we propose a general penalized variable selection strategy that simultaneously handles variable selection and parameter estimation in the PSH model. We rigorously establish the asymptotic properties of the proposed penalized estimators and modify the coordinate descent algorithm for implementation. Simulation studies are conducted to demonstrate the good performance of the proposed method. Data from deceased donor kidney transplants from the United Network of Organ Sharing illustrate the utility of the proposed method.

  14. Joint Bayesian variable and graph selection for regression models with network-structured predictors

    Science.gov (United States)

    Peterson, C. B.; Stingo, F. C.; Vannucci, M.

    2015-01-01

    In this work, we develop a Bayesian approach to perform selection of predictors that are linked within a network. We achieve this by combining a sparse regression model relating the predictors to a response variable with a graphical model describing conditional dependencies among the predictors. The proposed method is well-suited for genomic applications since it allows the identification of pathways of functionally related genes or proteins which impact an outcome of interest. In contrast to previous approaches for network-guided variable selection, we infer the network among predictors using a Gaussian graphical model and do not assume that network information is available a priori. We demonstrate that our method outperforms existing methods in identifying network-structured predictors in simulation settings, and illustrate our proposed model with an application to inference of proteins relevant to glioblastoma survival. PMID:26514925

  15. Variable Selection via Partial Correlation.

    Science.gov (United States)

    Li, Runze; Liu, Jingyuan; Lou, Lejia

    2017-07-01

    Partial correlation based variable selection method was proposed for normal linear regression models by Bühlmann, Kalisch and Maathuis (2010) as a comparable alternative method to regularization methods for variable selection. This paper addresses two important issues related to partial correlation based variable selection method: (a) whether this method is sensitive to normality assumption, and (b) whether this method is valid when the dimension of predictor increases in an exponential rate of the sample size. To address issue (a), we systematically study this method for elliptical linear regression models. Our finding indicates that the original proposal may lead to inferior performance when the marginal kurtosis of predictor is not close to that of normal distribution. Our simulation results further confirm this finding. To ensure the superior performance of partial correlation based variable selection procedure, we propose a thresholded partial correlation (TPC) approach to select significant variables in linear regression models. We establish the selection consistency of the TPC in the presence of ultrahigh dimensional predictors. Since the TPC procedure includes the original proposal as a special case, our theoretical results address the issue (b) directly. As a by-product, the sure screening property of the first step of TPC was obtained. The numerical examples also illustrate that the TPC is competitively comparable to the commonly-used regularization methods for variable selection.

  16. FIRE: an SPSS program for variable selection in multiple linear regression analysis via the relative importance of predictors.

    Science.gov (United States)

    Lorenzo-Seva, Urbano; Ferrando, Pere J

    2011-03-01

    We provide an SPSS program that implements currently recommended techniques and recent developments for selecting variables in multiple linear regression analysis via the relative importance of predictors. The approach consists of: (1) optimally splitting the data for cross-validation, (2) selecting the final set of predictors to be retained in the equation regression, and (3) assessing the behavior of the chosen model using standard indices and procedures. The SPSS syntax, a short manual, and data files related to this article are available as supplemental materials from brm.psychonomic-journals.org/content/supplemental.

  17. Variable selection methods in PLS regression - a comparison study on metabolomics data

    DEFF Research Database (Denmark)

    Karaman, İbrahim; Hedemann, Mette Skou; Knudsen, Knud Erik Bach

    . The aim of the metabolomics study was to investigate the metabolic profile in pigs fed various cereal fractions with special attention to the metabolism of lignans using LC-MS based metabolomic approach. References 1. Lê Cao KA, Rossouw D, Robert-Granié C, Besse P: A Sparse PLS for Variable Selection when...... integrated approach. Due to the high number of variables in data sets (both raw data and after peak picking) the selection of important variables in an explorative analysis is difficult, especially when different data sets of metabolomics data need to be related. Variable selection (or removal of irrelevant...... different strategies for variable selection on PLSR method were considered and compared with respect to selected subset of variables and the possibility for biological validation. Sparse PLSR [1] as well as PLSR with Jack-knifing [2] was applied to data in order to achieve variable selection prior...

  18. Variable importance in latent variable regression models

    NARCIS (Netherlands)

    Kvalheim, O.M.; Arneberg, R.; Bleie, O.; Rajalahti, T.; Smilde, A.K.; Westerhuis, J.A.

    2014-01-01

    The quality and practical usefulness of a regression model are a function of both interpretability and prediction performance. This work presents some new graphical tools for improved interpretation of latent variable regression models that can also assist in improved algorithms for variable

  19. Benchmarking Variable Selection in QSAR.

    Science.gov (United States)

    Eklund, Martin; Norinder, Ulf; Boyer, Scott; Carlsson, Lars

    2012-02-01

    Variable selection is important in QSAR modeling since it can improve model performance and transparency, as well as reduce the computational cost of model fitting and predictions. Which variable selection methods that perform well in QSAR settings is largely unknown. To address this question we, in a total of 1728 benchmarking experiments, rigorously investigated how eight variable selection methods affect the predictive performance and transparency of random forest models fitted to seven QSAR datasets covering different endpoints, descriptors sets, types of response variables, and number of chemical compounds. The results show that univariate variable selection methods are suboptimal and that the number of variables in the benchmarked datasets can be reduced with about 60 % without significant loss in model performance when using multivariate adaptive regression splines MARS and forward selection. Copyright © 2012 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

  20. Selecting a Regression Saturated by Indicators

    DEFF Research Database (Denmark)

    Hendry, David F.; Johansen, Søren; Santos, Carlos

    We consider selecting a regression model, using a variant of Gets, when there are more variables than observations, in the special case that the variables are impulse dummies (indicators) for every observation. We show that the setting is unproblematic if tackled appropriately, and obtain the fin...... the finite-sample distribution of estimators of the mean and variance in a simple location-scale model under the null that no impulses matter. A Monte Carlo simulation confirms the null distribution, and shows power against an alternative of interest....

  1. Selecting a Regression Saturated by Indicators

    DEFF Research Database (Denmark)

    Hendry, David F.; Johansen, Søren; Santos, Carlos

    We consider selecting a regression model, using a variant of Gets, when there are more variables than observations, in the special case that the variables are impulse dummies (indicators) for every observation. We show that the setting is unproblematic if tackled appropriately, and obtain the fin...... the finite-sample distribution of estimators of the mean and variance in a simple location-scale model under the null that no impulses matter. A Monte Carlo simulation confirms the null distribution, and shows power against an alternative of interest...

  2. Genetic variability, partial regression, Co-heritability studies and their implication in selection of high yielding potato gen

    International Nuclear Information System (INIS)

    Iqbal, Z.M.; Khan, S.A.

    2003-01-01

    Partial regression coefficient, genotypic and phenotypic variabilities, heritability co-heritability and genetic advance were studied in 15 Potato varieties of exotic and local origin. Both genotypic and phenotypic coefficients of variations were high for scab and rhizoctonia incidence percentage. Significant partial regression coefficient for emergence percentage indicated its relative importance in tuber yield. High heritability (broadsense) estimates coupled with high genetic advance for plant height, number of stems per plant and scab percentage revealed substantial contribution of additive genetic variance in the expression of these traits. Hence, the selection based on these characters could play a significant role in their improvement the dominance and epistatic variance was more important for character expression of yield ha/sup -1/, emergence and rhizoctonia percentage. This phenomenon is mainly due to the accumulative effects of low heritability and low to moderate genetic advance. The high co-heritability coupled with negative genotypic and phenotypic covariance revealed that selection of varieties having low scab and rhizoctonia percentage resulted in more potato yield. (author)

  3. Model building strategy for logistic regression: purposeful selection.

    Science.gov (United States)

    Zhang, Zhongheng

    2016-03-01

    Logistic regression is one of the most commonly used models to account for confounders in medical literature. The article introduces how to perform purposeful selection model building strategy with R. I stress on the use of likelihood ratio test to see whether deleting a variable will have significant impact on model fit. A deleted variable should also be checked for whether it is an important adjustment of remaining covariates. Interaction should be checked to disentangle complex relationship between covariates and their synergistic effect on response variable. Model should be checked for the goodness-of-fit (GOF). In other words, how the fitted model reflects the real data. Hosmer-Lemeshow GOF test is the most widely used for logistic regression model.

  4. Multi-omics facilitated variable selection in Cox-regression model for cancer prognosis prediction.

    Science.gov (United States)

    Liu, Cong; Wang, Xujun; Genchev, Georgi Z; Lu, Hui

    2017-07-15

    New developments in high-throughput genomic technologies have enabled the measurement of diverse types of omics biomarkers in a cost-efficient and clinically-feasible manner. Developing computational methods and tools for analysis and translation of such genomic data into clinically-relevant information is an ongoing and active area of investigation. For example, several studies have utilized an unsupervised learning framework to cluster patients by integrating omics data. Despite such recent advances, predicting cancer prognosis using integrated omics biomarkers remains a challenge. There is also a shortage of computational tools for predicting cancer prognosis by using supervised learning methods. The current standard approach is to fit a Cox regression model by concatenating the different types of omics data in a linear manner, while penalty could be added for feature selection. A more powerful approach, however, would be to incorporate data by considering relationships among omics datatypes. Here we developed two methods: a SKI-Cox method and a wLASSO-Cox method to incorporate the association among different types of omics data. Both methods fit the Cox proportional hazards model and predict a risk score based on mRNA expression profiles. SKI-Cox borrows the information generated by these additional types of omics data to guide variable selection, while wLASSO-Cox incorporates this information as a penalty factor during model fitting. We show that SKI-Cox and wLASSO-Cox models select more true variables than a LASSO-Cox model in simulation studies. We assess the performance of SKI-Cox and wLASSO-Cox using TCGA glioblastoma multiforme and lung adenocarcinoma data. In each case, mRNA expression, methylation, and copy number variation data are integrated to predict the overall survival time of cancer patients. Our methods achieve better performance in predicting patients' survival in glioblastoma and lung adenocarcinoma. Copyright © 2017. Published by Elsevier

  5. Interval ridge regression (iRR) as a fast and robust method for quantitative prediction and variable selection applied to edible oil adulteration.

    Science.gov (United States)

    Jović, Ozren; Smrečki, Neven; Popović, Zora

    2016-04-01

    A novel quantitative prediction and variable selection method called interval ridge regression (iRR) is studied in this work. The method is performed on six data sets of FTIR, two data sets of UV-vis and one data set of DSC. The obtained results show that models built with ridge regression on optimal variables selected with iRR significantly outperfom models built with ridge regression on all variables in both calibration (6 out of 9 cases) and validation (2 out of 9 cases). In this study, iRR is also compared with interval partial least squares regression (iPLS). iRR outperfomed iPLS in validation (insignificantly in 6 out of 9 cases and significantly in one out of 9 cases for poil, a well known health beneficial nutrient, is studied in this work by mixing it with cheap and widely used oils such as soybean (So) oil, rapeseed (R) oil and sunflower (Su) oil. Binary mixture sets of hempseed oil with these three oils (HSo, HR and HSu) and a ternary mixture set of H oil, R oil and Su oil (HRSu) were considered. The obtained accuracy indicates that using iRR on FTIR and UV-vis data, each particular oil can be very successfully quantified (in all 8 cases RMSEPoil (R(2)>0.99). Copyright © 2015 Elsevier B.V. All rights reserved.

  6. Variable selection in multivariate calibration based on clustering of variable concept.

    Science.gov (United States)

    Farrokhnia, Maryam; Karimi, Sadegh

    2016-01-01

    Recently we have proposed a new variable selection algorithm, based on clustering of variable concept (CLoVA) in classification problem. With the same idea, this new concept has been applied to a regression problem and then the obtained results have been compared with conventional variable selection strategies for PLS. The basic idea behind the clustering of variable is that, the instrument channels are clustered into different clusters via clustering algorithms. Then, the spectral data of each cluster are subjected to PLS regression. Different real data sets (Cargill corn, Biscuit dough, ACE QSAR, Soy, and Tablet) have been used to evaluate the influence of the clustering of variables on the prediction performances of PLS. Almost in the all cases, the statistical parameter especially in prediction error shows the superiority of CLoVA-PLS respect to other variable selection strategies. Finally the synergy clustering of variable (sCLoVA-PLS), which is used the combination of cluster, has been proposed as an efficient and modification of CLoVA algorithm. The obtained statistical parameter indicates that variable clustering can split useful part from redundant ones, and then based on informative cluster; stable model can be reached. Copyright © 2015 Elsevier B.V. All rights reserved.

  7. Model selection for semiparametric marginal mean regression accounting for within-cluster subsampling variability and informative cluster size.

    Science.gov (United States)

    Shen, Chung-Wei; Chen, Yi-Hau

    2018-03-13

    We propose a model selection criterion for semiparametric marginal mean regression based on generalized estimating equations. The work is motivated by a longitudinal study on the physical frailty outcome in the elderly, where the cluster size, that is, the number of the observed outcomes in each subject, is "informative" in the sense that it is related to the frailty outcome itself. The new proposal, called Resampling Cluster Information Criterion (RCIC), is based on the resampling idea utilized in the within-cluster resampling method (Hoffman, Sen, and Weinberg, 2001, Biometrika 88, 1121-1134) and accommodates informative cluster size. The implementation of RCIC, however, is free of performing actual resampling of the data and hence is computationally convenient. Compared with the existing model selection methods for marginal mean regression, the RCIC method incorporates an additional component accounting for variability of the model over within-cluster subsampling, and leads to remarkable improvements in selecting the correct model, regardless of whether the cluster size is informative or not. Applying the RCIC method to the longitudinal frailty study, we identify being female, old age, low income and life satisfaction, and chronic health conditions as significant risk factors for physical frailty in the elderly. © 2018, The International Biometric Society.

  8. On a Robust MaxEnt Process Regression Model with Sample-Selection

    Directory of Open Access Journals (Sweden)

    Hea-Jung Kim

    2018-04-01

    Full Text Available In a regression analysis, a sample-selection bias arises when a dependent variable is partially observed as a result of the sample selection. This study introduces a Maximum Entropy (MaxEnt process regression model that assumes a MaxEnt prior distribution for its nonparametric regression function and finds that the MaxEnt process regression model includes the well-known Gaussian process regression (GPR model as a special case. Then, this special MaxEnt process regression model, i.e., the GPR model, is generalized to obtain a robust sample-selection Gaussian process regression (RSGPR model that deals with non-normal data in the sample selection. Various properties of the RSGPR model are established, including the stochastic representation, distributional hierarchy, and magnitude of the sample-selection bias. These properties are used in the paper to develop a hierarchical Bayesian methodology to estimate the model. This involves a simple and computationally feasible Markov chain Monte Carlo algorithm that avoids analytical or numerical derivatives of the log-likelihood function of the model. The performance of the RSGPR model in terms of the sample-selection bias correction, robustness to non-normality, and prediction, is demonstrated through results in simulations that attest to its good finite-sample performance.

  9. Model selection in kernel ridge regression

    DEFF Research Database (Denmark)

    Exterkate, Peter

    2013-01-01

    Kernel ridge regression is a technique to perform ridge regression with a potentially infinite number of nonlinear transformations of the independent variables as regressors. This method is gaining popularity as a data-rich nonlinear forecasting tool, which is applicable in many different contexts....... The influence of the choice of kernel and the setting of tuning parameters on forecast accuracy is investigated. Several popular kernels are reviewed, including polynomial kernels, the Gaussian kernel, and the Sinc kernel. The latter two kernels are interpreted in terms of their smoothing properties......, and the tuning parameters associated to all these kernels are related to smoothness measures of the prediction function and to the signal-to-noise ratio. Based on these interpretations, guidelines are provided for selecting the tuning parameters from small grids using cross-validation. A Monte Carlo study...

  10. Statistical methods and regression analysis of stratospheric ozone and meteorological variables in Isfahan

    Science.gov (United States)

    Hassanzadeh, S.; Hosseinibalam, F.; Omidvari, M.

    2008-04-01

    Data of seven meteorological variables (relative humidity, wet temperature, dry temperature, maximum temperature, minimum temperature, ground temperature and sun radiation time) and ozone values have been used for statistical analysis. Meteorological variables and ozone values were analyzed using both multiple linear regression and principal component methods. Data for the period 1999-2004 are analyzed jointly using both methods. For all periods, temperature dependent variables were highly correlated, but were all negatively correlated with relative humidity. Multiple regression analysis was used to fit the meteorological variables using the meteorological variables as predictors. A variable selection method based on high loading of varimax rotated principal components was used to obtain subsets of the predictor variables to be included in the linear regression model of the meteorological variables. In 1999, 2001 and 2002 one of the meteorological variables was weakly influenced predominantly by the ozone concentrations. However, the model did not predict that the meteorological variables for the year 2000 were not influenced predominantly by the ozone concentrations that point to variation in sun radiation. This could be due to other factors that were not explicitly considered in this study.

  11. Variable selection in near-infrared spectroscopy: Benchmarking of feature selection methods on biodiesel data

    International Nuclear Information System (INIS)

    Balabin, Roman M.; Smirnov, Sergey V.

    2011-01-01

    During the past several years, near-infrared (near-IR/NIR) spectroscopy has increasingly been adopted as an analytical tool in various fields from petroleum to biomedical sectors. The NIR spectrum (above 4000 cm -1 ) of a sample is typically measured by modern instruments at a few hundred of wavelengths. Recently, considerable effort has been directed towards developing procedures to identify variables (wavelengths) that contribute useful information. Variable selection (VS) or feature selection, also called frequency selection or wavelength selection, is a critical step in data analysis for vibrational spectroscopy (infrared, Raman, or NIRS). In this paper, we compare the performance of 16 different feature selection methods for the prediction of properties of biodiesel fuel, including density, viscosity, methanol content, and water concentration. The feature selection algorithms tested include stepwise multiple linear regression (MLR-step), interval partial least squares regression (iPLS), backward iPLS (BiPLS), forward iPLS (FiPLS), moving window partial least squares regression (MWPLS), (modified) changeable size moving window partial least squares (CSMWPLS/MCSMWPLSR), searching combination moving window partial least squares (SCMWPLS), successive projections algorithm (SPA), uninformative variable elimination (UVE, including UVE-SPA), simulated annealing (SA), back-propagation artificial neural networks (BP-ANN), Kohonen artificial neural network (K-ANN), and genetic algorithms (GAs, including GA-iPLS). Two linear techniques for calibration model building, namely multiple linear regression (MLR) and partial least squares regression/projection to latent structures (PLS/PLSR), are used for the evaluation of biofuel properties. A comparison with a non-linear calibration model, artificial neural networks (ANN-MLP), is also provided. Discussion of gasoline, ethanol-gasoline (bioethanol), and diesel fuel data is presented. The results of other spectroscopic

  12. A Demonstration of Regression False Positive Selection in Data Mining

    Science.gov (United States)

    Pinder, Jonathan P.

    2014-01-01

    Business analytics courses, such as marketing research, data mining, forecasting, and advanced financial modeling, have substantial predictive modeling components. The predictive modeling in these courses requires students to estimate and test many linear regressions. As a result, false positive variable selection ("type I errors") is…

  13. Automatic selection of indicators in a fully saturated regression

    DEFF Research Database (Denmark)

    Hendry, David F.; Johansen, Søren; Santos, Carlos

    2008-01-01

    We consider selecting a regression model, using a variant of Gets, when there are more variables than observations, in the special case that the variables are impulse dummies (indicators) for every observation. We show that the setting is unproblematic if tackled appropriately, and obtain the fin...... the finite-sample distribution of estimators of the mean and variance in a simple location-scale model under the null that no impulses matter. A Monte Carlo simulation confirms the null distribution, and shows power against an alternative of interest....

  14. Uninformative variable elimination assisted by Gram-Schmidt Orthogonalization/successive projection algorithm for descriptor selection in QSAR

    DEFF Research Database (Denmark)

    Omidikia, Nematollah; Kompany-Zareh, Mohsen

    2013-01-01

    Employment of Uninformative Variable Elimination (UVE) as a robust variable selection method is reported in this study. Each regression coefficient represents the contribution of the corresponding variable in the established model, but in the presence of uninformative variables as well as colline......Employment of Uninformative Variable Elimination (UVE) as a robust variable selection method is reported in this study. Each regression coefficient represents the contribution of the corresponding variable in the established model, but in the presence of uninformative variables as well...... as collinearity reliability of the regression coefficient's magnitude is suspicious. Successive Projection Algorithm (SPA) and Gram-Schmidt Orthogonalization (GSO) were implemented as pre-selection technique for removing collinearity and redundancy among variables in the model. Uninformative variable elimination...

  15. Integrated Multiscale Latent Variable Regression and Application to Distillation Columns

    Directory of Open Access Journals (Sweden)

    Muddu Madakyaru

    2013-01-01

    Full Text Available Proper control of distillation columns requires estimating some key variables that are challenging to measure online (such as compositions, which are usually estimated using inferential models. Commonly used inferential models include latent variable regression (LVR techniques, such as principal component regression (PCR, partial least squares (PLS, and regularized canonical correlation analysis (RCCA. Unfortunately, measured practical data are usually contaminated with errors, which degrade the prediction abilities of inferential models. Therefore, noisy measurements need to be filtered to enhance the prediction accuracy of these models. Multiscale filtering has been shown to be a powerful feature extraction tool. In this work, the advantages of multiscale filtering are utilized to enhance the prediction accuracy of LVR models by developing an integrated multiscale LVR (IMSLVR modeling algorithm that integrates modeling and feature extraction. The idea behind the IMSLVR modeling algorithm is to filter the process data at different decomposition levels, model the filtered data from each level, and then select the LVR model that optimizes a model selection criterion. The performance of the developed IMSLVR algorithm is illustrated using three examples, one using synthetic data, one using simulated distillation column data, and one using experimental packed bed distillation column data. All examples clearly demonstrate the effectiveness of the IMSLVR algorithm over the conventional methods.

  16. Order Selection for General Expression of Nonlinear Autoregressive Model Based on Multivariate Stepwise Regression

    Science.gov (United States)

    Shi, Jinfei; Zhu, Songqing; Chen, Ruwen

    2017-12-01

    An order selection method based on multiple stepwise regressions is proposed for General Expression of Nonlinear Autoregressive model which converts the model order problem into the variable selection of multiple linear regression equation. The partial autocorrelation function is adopted to define the linear term in GNAR model. The result is set as the initial model, and then the nonlinear terms are introduced gradually. Statistics are chosen to study the improvements of both the new introduced and originally existed variables for the model characteristics, which are adopted to determine the model variables to retain or eliminate. So the optimal model is obtained through data fitting effect measurement or significance test. The simulation and classic time-series data experiment results show that the method proposed is simple, reliable and can be applied to practical engineering.

  17. transformation of independent variables in polynomial regression ...

    African Journals Online (AJOL)

    Ada

    preferable when possible to work with a simple functional form in transformed variables rather than with a more complicated form in the original variables. In this paper, it is shown that linear transformations applied to independent variables in polynomial regression models affect the t ratio and hence the statistical ...

  18. A PANEL REGRESSION ANALYSIS OF HUMAN CAPITAL RELEVANCE IN SELECTED SCANDINAVIAN AND SE EUROPEAN COUNTRIES

    Directory of Open Access Journals (Sweden)

    Filip Kokotovic

    2016-06-01

    Full Text Available The study of human capital relevance to economic growth is becoming increasingly important taking into account its relevance in many of the Sustainable Development Goals proposed by the UN. This paper conducted a panel regression analysis of selected SE European countries and Scandinavian countries using the Granger causality test and pooled panel regression. In order to test the relevance of human capital on economic growth, several human capital proxy variables were identified. Aside from the human capital proxy variables, other explanatory variables were selected using stepwise regression while the dependant variable was GDP. This paper concludes that there are significant structural differences in the economies of the two observed panels. Of the human capital proxy variables observed, for the panel of SE European countries only life expectancy was statistically significant and it had a negative impact on economic growth, while in the panel of Scandinavian countries total public expenditure on education had a statistically significant positive effect on economic growth. Based upon these results and existing studies, this paper concludes that human capital has a far more significant impact on economic growth in more developed economies.

  19. Comparison of Sparse and Jack-knife partial least squares regression methods for variable selection

    DEFF Research Database (Denmark)

    Karaman, Ibrahim; Qannari, El Mostafa; Martens, Harald

    2013-01-01

    The objective of this study was to compare two different techniques of variable selection, Sparse PLSR and Jack-knife PLSR, with respect to their predictive ability and their ability to identify relevant variables. Sparse PLSR is a method that is frequently used in genomics, whereas Jack-knife PL...

  20. Bayesian Group Bridge for Bi-level Variable Selection.

    Science.gov (United States)

    Mallick, Himel; Yi, Nengjun

    2017-06-01

    A Bayesian bi-level variable selection method (BAGB: Bayesian Analysis of Group Bridge) is developed for regularized regression and classification. This new development is motivated by grouped data, where generic variables can be divided into multiple groups, with variables in the same group being mechanistically related or statistically correlated. As an alternative to frequentist group variable selection methods, BAGB incorporates structural information among predictors through a group-wise shrinkage prior. Posterior computation proceeds via an efficient MCMC algorithm. In addition to the usual ease-of-interpretation of hierarchical linear models, the Bayesian formulation produces valid standard errors, a feature that is notably absent in the frequentist framework. Empirical evidence of the attractiveness of the method is illustrated by extensive Monte Carlo simulations and real data analysis. Finally, several extensions of this new approach are presented, providing a unified framework for bi-level variable selection in general models with flexible penalties.

  1. Cross-validation pitfalls when selecting and assessing regression and classification models.

    Science.gov (United States)

    Krstajic, Damjan; Buturovic, Ljubomir J; Leahy, David E; Thomas, Simon

    2014-03-29

    We address the problem of selecting and assessing classification and regression models using cross-validation. Current state-of-the-art methods can yield models with high variance, rendering them unsuitable for a number of practical applications including QSAR. In this paper we describe and evaluate best practices which improve reliability and increase confidence in selected models. A key operational component of the proposed methods is cloud computing which enables routine use of previously infeasible approaches. We describe in detail an algorithm for repeated grid-search V-fold cross-validation for parameter tuning in classification and regression, and we define a repeated nested cross-validation algorithm for model assessment. As regards variable selection and parameter tuning we define two algorithms (repeated grid-search cross-validation and double cross-validation), and provide arguments for using the repeated grid-search in the general case. We show results of our algorithms on seven QSAR datasets. The variation of the prediction performance, which is the result of choosing different splits of the dataset in V-fold cross-validation, needs to be taken into account when selecting and assessing classification and regression models. We demonstrate the importance of repeating cross-validation when selecting an optimal model, as well as the importance of repeating nested cross-validation when assessing a prediction error.

  2. A Monte Carlo simulation study comparing linear regression, beta regression, variable-dispersion beta regression and fractional logit regression at recovering average difference measures in a two sample design.

    Science.gov (United States)

    Meaney, Christopher; Moineddin, Rahim

    2014-01-24

    In biomedical research, response variables are often encountered which have bounded support on the open unit interval--(0,1). Traditionally, researchers have attempted to estimate covariate effects on these types of response data using linear regression. Alternative modelling strategies may include: beta regression, variable-dispersion beta regression, and fractional logit regression models. This study employs a Monte Carlo simulation design to compare the statistical properties of the linear regression model to that of the more novel beta regression, variable-dispersion beta regression, and fractional logit regression models. In the Monte Carlo experiment we assume a simple two sample design. We assume observations are realizations of independent draws from their respective probability models. The randomly simulated draws from the various probability models are chosen to emulate average proportion/percentage/rate differences of pre-specified magnitudes. Following simulation of the experimental data we estimate average proportion/percentage/rate differences. We compare the estimators in terms of bias, variance, type-1 error and power. Estimates of Monte Carlo error associated with these quantities are provided. If response data are beta distributed with constant dispersion parameters across the two samples, then all models are unbiased and have reasonable type-1 error rates and power profiles. If the response data in the two samples have different dispersion parameters, then the simple beta regression model is biased. When the sample size is small (N0 = N1 = 25) linear regression has superior type-1 error rates compared to the other models. Small sample type-1 error rates can be improved in beta regression models using bias correction/reduction methods. In the power experiments, variable-dispersion beta regression and fractional logit regression models have slightly elevated power compared to linear regression models. Similar results were observed if the

  3. Variable selection and estimation for longitudinal survey data

    KAUST Repository

    Wang, Li

    2014-09-01

    There is wide interest in studying longitudinal surveys where sample subjects are observed successively over time. Longitudinal surveys have been used in many areas today, for example, in the health and social sciences, to explore relationships or to identify significant variables in regression settings. This paper develops a general strategy for the model selection problem in longitudinal sample surveys. A survey weighted penalized estimating equation approach is proposed to select significant variables and estimate the coefficients simultaneously. The proposed estimators are design consistent and perform as well as the oracle procedure when the correct submodel was known. The estimating function bootstrap is applied to obtain the standard errors of the estimated parameters with good accuracy. A fast and efficient variable selection algorithm is developed to identify significant variables for complex longitudinal survey data. Simulated examples are illustrated to show the usefulness of the proposed methodology under various model settings and sampling designs. © 2014 Elsevier Inc.

  4. Subset selection in regression

    CERN Document Server

    Miller, Alan

    2002-01-01

    Originally published in 1990, the first edition of Subset Selection in Regression filled a significant gap in the literature, and its critical and popular success has continued for more than a decade. Thoroughly revised to reflect progress in theory, methods, and computing power, the second edition promises to continue that tradition. The author has thoroughly updated each chapter, incorporated new material on recent developments, and included more examples and references. New in the Second Edition:A separate chapter on Bayesian methodsComplete revision of the chapter on estimationA major example from the field of near infrared spectroscopyMore emphasis on cross-validationGreater focus on bootstrappingStochastic algorithms for finding good subsets from large numbers of predictors when an exhaustive search is not feasible Software available on the Internet for implementing many of the algorithms presentedMore examplesSubset Selection in Regression, Second Edition remains dedicated to the techniques for fitting...

  5. How Robust Is Linear Regression with Dummy Variables?

    Science.gov (United States)

    Blankmeyer, Eric

    2006-01-01

    Researchers in education and the social sciences make extensive use of linear regression models in which the dependent variable is continuous-valued while the explanatory variables are a combination of continuous-valued regressors and dummy variables. The dummies partition the sample into groups, some of which may contain only a few observations.…

  6. The use of vector bootstrapping to improve variable selection precision in Lasso models

    NARCIS (Netherlands)

    Laurin, C.; Boomsma, D.I.; Lubke, G.H.

    2016-01-01

    The Lasso is a shrinkage regression method that is widely used for variable selection in statistical genetics. Commonly, K-fold cross-validation is used to fit a Lasso model. This is sometimes followed by using bootstrap confidence intervals to improve precision in the resulting variable selections.

  7. Bayesian site selection for fast Gaussian process regression

    KAUST Repository

    Pourhabib, Arash; Liang, Faming; Ding, Yu

    2014-01-01

    Gaussian Process (GP) regression is a popular method in the field of machine learning and computer experiment designs; however, its ability to handle large data sets is hindered by the computational difficulty in inverting a large covariance matrix. Likelihood approximation methods were developed as a fast GP approximation, thereby reducing the computation cost of GP regression by utilizing a much smaller set of unobserved latent variables called pseudo points. This article reports a further improvement to the likelihood approximation methods by simultaneously deciding both the number and locations of the pseudo points. The proposed approach is a Bayesian site selection method where both the number and locations of the pseudo inputs are parameters in the model, and the Bayesian model is solved using a reversible jump Markov chain Monte Carlo technique. Through a number of simulated and real data sets, it is demonstrated that with appropriate priors chosen, the Bayesian site selection method can produce a good balance between computation time and prediction accuracy: it is fast enough to handle large data sets that a full GP is unable to handle, and it improves, quite often remarkably, the prediction accuracy, compared with the existing likelihood approximations. © 2014 Taylor and Francis Group, LLC.

  8. Bayesian site selection for fast Gaussian process regression

    KAUST Repository

    Pourhabib, Arash

    2014-02-05

    Gaussian Process (GP) regression is a popular method in the field of machine learning and computer experiment designs; however, its ability to handle large data sets is hindered by the computational difficulty in inverting a large covariance matrix. Likelihood approximation methods were developed as a fast GP approximation, thereby reducing the computation cost of GP regression by utilizing a much smaller set of unobserved latent variables called pseudo points. This article reports a further improvement to the likelihood approximation methods by simultaneously deciding both the number and locations of the pseudo points. The proposed approach is a Bayesian site selection method where both the number and locations of the pseudo inputs are parameters in the model, and the Bayesian model is solved using a reversible jump Markov chain Monte Carlo technique. Through a number of simulated and real data sets, it is demonstrated that with appropriate priors chosen, the Bayesian site selection method can produce a good balance between computation time and prediction accuracy: it is fast enough to handle large data sets that a full GP is unable to handle, and it improves, quite often remarkably, the prediction accuracy, compared with the existing likelihood approximations. © 2014 Taylor and Francis Group, LLC.

  9. Meta-Statistics for Variable Selection: The R Package BioMark

    Directory of Open Access Journals (Sweden)

    Ron Wehrens

    2012-11-01

    Full Text Available Biomarker identification is an ever more important topic in the life sciences. With the advent of measurement methodologies based on microarrays and mass spectrometry, thousands of variables are routinely being measured on complex biological samples. Often, the question is what makes two groups of samples different. Classical hypothesis testing suffers from the multiple testing problem; however, correcting for this often leads to a lack of power. In addition, choosing α cutoff levels remains somewhat arbitrary. Also in a regression context, a model depending on few but relevant variables will be more accurate and precise, and easier to interpret biologically.We propose an R package, BioMark, implementing two meta-statistics for variable selection. The first, higher criticism, presents a data-dependent selection threshold for significance, instead of a cookbook value of α = 0.05. It is applicable in all cases where two groups are compared. The second, stability selection, is more general, and can also be applied in a regression context. This approach uses repeated subsampling of the data in order to assess the variability of the model coefficients and selects those that remain consistently important. It is shown using experimental spike-in data from the field of metabolomics that both approaches work well with real data. BioMark also contains functionality for simulating data with specific characteristics for algorithm development and testing.

  10. Regression calibration with more surrogates than mismeasured variables

    KAUST Repository

    Kipnis, Victor

    2012-06-29

    In a recent paper (Weller EA, Milton DK, Eisen EA, Spiegelman D. Regression calibration for logistic regression with multiple surrogates for one exposure. Journal of Statistical Planning and Inference 2007; 137: 449-461), the authors discussed fitting logistic regression models when a scalar main explanatory variable is measured with error by several surrogates, that is, a situation with more surrogates than variables measured with error. They compared two methods of adjusting for measurement error using a regression calibration approximate model as if it were exact. One is the standard regression calibration approach consisting of substituting an estimated conditional expectation of the true covariate given observed data in the logistic regression. The other is a novel two-stage approach when the logistic regression is fitted to multiple surrogates, and then a linear combination of estimated slopes is formed as the estimate of interest. Applying estimated asymptotic variances for both methods in a single data set with some sensitivity analysis, the authors asserted superiority of their two-stage approach. We investigate this claim in some detail. A troubling aspect of the proposed two-stage method is that, unlike standard regression calibration and a natural form of maximum likelihood, the resulting estimates are not invariant to reparameterization of nuisance parameters in the model. We show, however, that, under the regression calibration approximation, the two-stage method is asymptotically equivalent to a maximum likelihood formulation, and is therefore in theory superior to standard regression calibration. However, our extensive finite-sample simulations in the practically important parameter space where the regression calibration model provides a good approximation failed to uncover such superiority of the two-stage method. We also discuss extensions to different data structures.

  11. Regression calibration with more surrogates than mismeasured variables

    KAUST Repository

    Kipnis, Victor; Midthune, Douglas; Freedman, Laurence S.; Carroll, Raymond J.

    2012-01-01

    In a recent paper (Weller EA, Milton DK, Eisen EA, Spiegelman D. Regression calibration for logistic regression with multiple surrogates for one exposure. Journal of Statistical Planning and Inference 2007; 137: 449-461), the authors discussed fitting logistic regression models when a scalar main explanatory variable is measured with error by several surrogates, that is, a situation with more surrogates than variables measured with error. They compared two methods of adjusting for measurement error using a regression calibration approximate model as if it were exact. One is the standard regression calibration approach consisting of substituting an estimated conditional expectation of the true covariate given observed data in the logistic regression. The other is a novel two-stage approach when the logistic regression is fitted to multiple surrogates, and then a linear combination of estimated slopes is formed as the estimate of interest. Applying estimated asymptotic variances for both methods in a single data set with some sensitivity analysis, the authors asserted superiority of their two-stage approach. We investigate this claim in some detail. A troubling aspect of the proposed two-stage method is that, unlike standard regression calibration and a natural form of maximum likelihood, the resulting estimates are not invariant to reparameterization of nuisance parameters in the model. We show, however, that, under the regression calibration approximation, the two-stage method is asymptotically equivalent to a maximum likelihood formulation, and is therefore in theory superior to standard regression calibration. However, our extensive finite-sample simulations in the practically important parameter space where the regression calibration model provides a good approximation failed to uncover such superiority of the two-stage method. We also discuss extensions to different data structures.

  12. Bayesian Multiresolution Variable Selection for Ultra-High Dimensional Neuroimaging Data.

    Science.gov (United States)

    Zhao, Yize; Kang, Jian; Long, Qi

    2018-01-01

    Ultra-high dimensional variable selection has become increasingly important in analysis of neuroimaging data. For example, in the Autism Brain Imaging Data Exchange (ABIDE) study, neuroscientists are interested in identifying important biomarkers for early detection of the autism spectrum disorder (ASD) using high resolution brain images that include hundreds of thousands voxels. However, most existing methods are not feasible for solving this problem due to their extensive computational costs. In this work, we propose a novel multiresolution variable selection procedure under a Bayesian probit regression framework. It recursively uses posterior samples for coarser-scale variable selection to guide the posterior inference on finer-scale variable selection, leading to very efficient Markov chain Monte Carlo (MCMC) algorithms. The proposed algorithms are computationally feasible for ultra-high dimensional data. Also, our model incorporates two levels of structural information into variable selection using Ising priors: the spatial dependence between voxels and the functional connectivity between anatomical brain regions. Applied to the resting state functional magnetic resonance imaging (R-fMRI) data in the ABIDE study, our methods identify voxel-level imaging biomarkers highly predictive of the ASD, which are biologically meaningful and interpretable. Extensive simulations also show that our methods achieve better performance in variable selection compared to existing methods.

  13. Regional regression models of percentile flows for the contiguous United States: Expert versus data-driven independent variable selection

    Directory of Open Access Journals (Sweden)

    Geoffrey Fouad

    2018-06-01

    New hydrological insights for the region: A set of three variables selected based on an expert assessment of factors that influence percentile flows performed similarly to larger sets of variables selected using a data-driven method. Expert assessment variables included mean annual precipitation, potential evapotranspiration, and baseflow index. Larger sets of up to 37 variables contributed little, if any, additional predictive information. Variables used to describe the distribution of basin data (e.g. standard deviation were not useful, and average values were sufficient to characterize physical and climatic basin conditions. Effectiveness of the expert assessment variables may be due to the high degree of multicollinearity (i.e. cross-correlation among additional variables. A tool is provided in the Supplementary material to predict percentile flows based on the three expert assessment variables. Future work should develop new variables with a strong understanding of the processes related to percentile flows.

  14. Boosted beta regression.

    Directory of Open Access Journals (Sweden)

    Matthias Schmid

    Full Text Available Regression analysis with a bounded outcome is a common problem in applied statistics. Typical examples include regression models for percentage outcomes and the analysis of ratings that are measured on a bounded scale. In this paper, we consider beta regression, which is a generalization of logit models to situations where the response is continuous on the interval (0,1. Consequently, beta regression is a convenient tool for analyzing percentage responses. The classical approach to fit a beta regression model is to use maximum likelihood estimation with subsequent AIC-based variable selection. As an alternative to this established - yet unstable - approach, we propose a new estimation technique called boosted beta regression. With boosted beta regression estimation and variable selection can be carried out simultaneously in a highly efficient way. Additionally, both the mean and the variance of a percentage response can be modeled using flexible nonlinear covariate effects. As a consequence, the new method accounts for common problems such as overdispersion and non-binomial variance structures.

  15. Ensembling Variable Selectors by Stability Selection for the Cox Model

    Directory of Open Access Journals (Sweden)

    Qing-Yan Yin

    2017-01-01

    Full Text Available As a pivotal tool to build interpretive models, variable selection plays an increasingly important role in high-dimensional data analysis. In recent years, variable selection ensembles (VSEs have gained much interest due to their many advantages. Stability selection (Meinshausen and Bühlmann, 2010, a VSE technique based on subsampling in combination with a base algorithm like lasso, is an effective method to control false discovery rate (FDR and to improve selection accuracy in linear regression models. By adopting lasso as a base learner, we attempt to extend stability selection to handle variable selection problems in a Cox model. According to our experience, it is crucial to set the regularization region Λ in lasso and the parameter λmin properly so that stability selection can work well. To the best of our knowledge, however, there is no literature addressing this problem in an explicit way. Therefore, we first provide a detailed procedure to specify Λ and λmin. Then, some simulated and real-world data with various censoring rates are used to examine how well stability selection performs. It is also compared with several other variable selection approaches. Experimental results demonstrate that it achieves better or competitive performance in comparison with several other popular techniques.

  16. The number of subjects per variable required in linear regression analyses

    NARCIS (Netherlands)

    P.C. Austin (Peter); E.W. Steyerberg (Ewout)

    2015-01-01

    textabstractObjectives To determine the number of independent variables that can be included in a linear regression model. Study Design and Setting We used a series of Monte Carlo simulations to examine the impact of the number of subjects per variable (SPV) on the accuracy of estimated regression

  17. Bayesian approach to errors-in-variables in regression models

    Science.gov (United States)

    Rozliman, Nur Aainaa; Ibrahim, Adriana Irawati Nur; Yunus, Rossita Mohammad

    2017-05-01

    In many applications and experiments, data sets are often contaminated with error or mismeasured covariates. When at least one of the covariates in a model is measured with error, Errors-in-Variables (EIV) model can be used. Measurement error, when not corrected, would cause misleading statistical inferences and analysis. Therefore, our goal is to examine the relationship of the outcome variable and the unobserved exposure variable given the observed mismeasured surrogate by applying the Bayesian formulation to the EIV model. We shall extend the flexible parametric method proposed by Hossain and Gustafson (2009) to another nonlinear regression model which is the Poisson regression model. We shall then illustrate the application of this approach via a simulation study using Markov chain Monte Carlo sampling methods.

  18. Independent variable complexity for regional regression of the flow duration curve in ungauged basins

    Science.gov (United States)

    Fouad, Geoffrey; Skupin, André; Hope, Allen

    2016-04-01

    The flow duration curve (FDC) is one of the most widely used tools to quantify streamflow. Its percentile flows are often required for water resource applications, but these values must be predicted for ungauged basins with insufficient or no streamflow data. Regional regression is a commonly used approach for predicting percentile flows that involves identifying hydrologic regions and calibrating regression models to each region. The independent variables used to describe the physiographic and climatic setting of the basins are a critical component of regional regression, yet few studies have investigated their effect on resulting predictions. In this study, the complexity of the independent variables needed for regional regression is investigated. Different levels of variable complexity are applied for a regional regression consisting of 918 basins in the US. Both the hydrologic regions and regression models are determined according to the different sets of variables, and the accuracy of resulting predictions is assessed. The different sets of variables include (1) a simple set of three variables strongly tied to the FDC (mean annual precipitation, potential evapotranspiration, and baseflow index), (2) a traditional set of variables describing the average physiographic and climatic conditions of the basins, and (3) a more complex set of variables extending the traditional variables to include statistics describing the distribution of physiographic data and temporal components of climatic data. The latter set of variables is not typically used in regional regression, and is evaluated for its potential to predict percentile flows. The simplest set of only three variables performed similarly to the other more complex sets of variables. Traditional variables used to describe climate, topography, and soil offered little more to the predictions, and the experimental set of variables describing the distribution of basin data in more detail did not improve predictions

  19. [Correlation coefficient-based classification method of hydrological dependence variability: With auto-regression model as example].

    Science.gov (United States)

    Zhao, Yu Xi; Xie, Ping; Sang, Yan Fang; Wu, Zi Yi

    2018-04-01

    Hydrological process evaluation is temporal dependent. Hydrological time series including dependence components do not meet the data consistency assumption for hydrological computation. Both of those factors cause great difficulty for water researches. Given the existence of hydrological dependence variability, we proposed a correlationcoefficient-based method for significance evaluation of hydrological dependence based on auto-regression model. By calculating the correlation coefficient between the original series and its dependence component and selecting reasonable thresholds of correlation coefficient, this method divided significance degree of dependence into no variability, weak variability, mid variability, strong variability, and drastic variability. By deducing the relationship between correlation coefficient and auto-correlation coefficient in each order of series, we found that the correlation coefficient was mainly determined by the magnitude of auto-correlation coefficient from the 1 order to p order, which clarified the theoretical basis of this method. With the first-order and second-order auto-regression models as examples, the reasonability of the deduced formula was verified through Monte-Carlo experiments to classify the relationship between correlation coefficient and auto-correlation coefficient. This method was used to analyze three observed hydrological time series. The results indicated the coexistence of stochastic and dependence characteristics in hydrological process.

  20. SOCP relaxation bounds for the optimal subset selection problem applied to robust linear regression

    OpenAIRE

    Flores, Salvador

    2015-01-01

    This paper deals with the problem of finding the globally optimal subset of h elements from a larger set of n elements in d space dimensions so as to minimize a quadratic criterion, with an special emphasis on applications to computing the Least Trimmed Squares Estimator (LTSE) for robust regression. The computation of the LTSE is a challenging subset selection problem involving a nonlinear program with continuous and binary variables, linked in a highly nonlinear fashion. The selection of a ...

  1. Combining epidemiologic and biostatistical tools to enhance variable selection in HIV cohort analyses.

    Directory of Open Access Journals (Sweden)

    Christopher Rentsch

    Full Text Available BACKGROUND: Variable selection is an important step in building a multivariate regression model for which several methods and statistical packages are available. A comprehensive approach for variable selection in complex multivariate regression analyses within HIV cohorts is explored by utilizing both epidemiological and biostatistical procedures. METHODS: Three different methods for variable selection were illustrated in a study comparing survival time between subjects in the Department of Defense's National History Study and the Atlanta Veterans Affairs Medical Center's HIV Atlanta VA Cohort Study. The first two methods were stepwise selection procedures, based either on significance tests (Score test, or on information theory (Akaike Information Criterion, while the third method employed a Bayesian argument (Bayesian Model Averaging. RESULTS: All three methods resulted in a similar parsimonious survival model. Three of the covariates previously used in the multivariate model were not included in the final model suggested by the three approaches. When comparing the parsimonious model to the previously published model, there was evidence of less variance in the main survival estimates. CONCLUSIONS: The variable selection approaches considered in this study allowed building a model based on significance tests, on an information criterion, and on averaging models using their posterior probabilities. A parsimonious model that balanced these three approaches was found to provide a better fit than the previously reported model.

  2. Variable selection in multiple linear regression: The influence of ...

    African Journals Online (AJOL)

    provide an indication of whether the fit of the selected model improves or ... and calculate M(−i); quantify the influence of case i in terms of a function, f(•), of M and ..... [21] Venter JH & Snyman JLJ, 1997, Linear model selection based on risk ...

  3. Estimating nonlinear selection gradients using quadratic regression coefficients: double or nothing?

    Science.gov (United States)

    Stinchcombe, John R; Agrawal, Aneil F; Hohenlohe, Paul A; Arnold, Stevan J; Blows, Mark W

    2008-09-01

    The use of regression analysis has been instrumental in allowing evolutionary biologists to estimate the strength and mode of natural selection. Although directional and correlational selection gradients are equal to their corresponding regression coefficients, quadratic regression coefficients must be doubled to estimate stabilizing/disruptive selection gradients. Based on a sample of 33 papers published in Evolution between 2002 and 2007, at least 78% of papers have not doubled quadratic regression coefficients, leading to an appreciable underestimate of the strength of stabilizing and disruptive selection. Proper treatment of quadratic regression coefficients is necessary for estimation of fitness surfaces and contour plots, canonical analysis of the gamma matrix, and modeling the evolution of populations on an adaptive landscape.

  4. The number of subjects per variable required in linear regression analyses.

    Science.gov (United States)

    Austin, Peter C; Steyerberg, Ewout W

    2015-06-01

    To determine the number of independent variables that can be included in a linear regression model. We used a series of Monte Carlo simulations to examine the impact of the number of subjects per variable (SPV) on the accuracy of estimated regression coefficients and standard errors, on the empirical coverage of estimated confidence intervals, and on the accuracy of the estimated R(2) of the fitted model. A minimum of approximately two SPV tended to result in estimation of regression coefficients with relative bias of less than 10%. Furthermore, with this minimum number of SPV, the standard errors of the regression coefficients were accurately estimated and estimated confidence intervals had approximately the advertised coverage rates. A much higher number of SPV were necessary to minimize bias in estimating the model R(2), although adjusted R(2) estimates behaved well. The bias in estimating the model R(2) statistic was inversely proportional to the magnitude of the proportion of variation explained by the population regression model. Linear regression models require only two SPV for adequate estimation of regression coefficients, standard errors, and confidence intervals. Copyright © 2015 The Authors. Published by Elsevier Inc. All rights reserved.

  5. Improved intact soil-core carbon determination applying regression shrinkage and variable selection techniques to complete spectrum laser-induced breakdown spectroscopy (LIBS).

    Science.gov (United States)

    Bricklemyer, Ross S; Brown, David J; Turk, Philip J; Clegg, Sam M

    2013-10-01

    Laser-induced breakdown spectroscopy (LIBS) provides a potential method for rapid, in situ soil C measurement. In previous research on the application of LIBS to intact soil cores, we hypothesized that ultraviolet (UV) spectrum LIBS (200-300 nm) might not provide sufficient elemental information to reliably discriminate between soil organic C (SOC) and inorganic C (IC). In this study, using a custom complete spectrum (245-925 nm) core-scanning LIBS instrument, we analyzed 60 intact soil cores from six wheat fields. Predictive multi-response partial least squares (PLS2) models using full and reduced spectrum LIBS were compared for directly determining soil total C (TC), IC, and SOC. Two regression shrinkage and variable selection approaches, the least absolute shrinkage and selection operator (LASSO) and sparse multivariate regression with covariance estimation (MRCE), were tested for soil C predictions and the identification of wavelengths important for soil C prediction. Using complete spectrum LIBS for PLS2 modeling reduced the calibration standard error of prediction (SEP) 15 and 19% for TC and IC, respectively, compared to UV spectrum LIBS. The LASSO and MRCE approaches provided significantly improved calibration accuracy and reduced SEP 32-55% over UV spectrum PLS2 models. We conclude that (1) complete spectrum LIBS is superior to UV spectrum LIBS for predicting soil C for intact soil cores without pretreatment; (2) LASSO and MRCE approaches provide improved calibration prediction accuracy over PLS2 but require additional testing with increased soil and target analyte diversity; and (3) measurement errors associated with analyzing intact cores (e.g., sample density and surface roughness) require further study and quantification.

  6. Mahalanobis distance and variable selection to optimize dose response

    International Nuclear Information System (INIS)

    Moore, D.H. II; Bennett, D.E.; Wyrobek, A.J.; Kranzler, D.

    1979-01-01

    A battery of statistical techniques are combined to improve detection of low-level dose response. First, Mahalanobis distances are used to classify objects as normal or abnormal. Then the proportion classified abnormal is regressed on dose. Finally, a subset of regressor variables is selected which maximizes the slope of the dose response line. Use of the techniques is illustrated by application to mouse sperm damaged by low doses of x-rays

  7. A survey of variable selection methods in two Chinese epidemiology journals

    Directory of Open Access Journals (Sweden)

    Lynn Henry S

    2010-09-01

    Full Text Available Abstract Background Although much has been written on developing better procedures for variable selection, there is little research on how it is practiced in actual studies. This review surveys the variable selection methods reported in two high-ranking Chinese epidemiology journals. Methods Articles published in 2004, 2006, and 2008 in the Chinese Journal of Epidemiology and the Chinese Journal of Preventive Medicine were reviewed. Five categories of methods were identified whereby variables were selected using: A - bivariate analyses; B - multivariable analysis; e.g. stepwise or individual significance testing of model coefficients; C - first bivariate analyses, followed by multivariable analysis; D - bivariate analyses or multivariable analysis; and E - other criteria like prior knowledge or personal judgment. Results Among the 287 articles that reported using variable selection methods, 6%, 26%, 30%, 21%, and 17% were in categories A through E, respectively. One hundred sixty-three studies selected variables using bivariate analyses, 80% (130/163 via multiple significance testing at the 5% alpha-level. Of the 219 multivariable analyses, 97 (44% used stepwise procedures, 89 (41% tested individual regression coefficients, but 33 (15% did not mention how variables were selected. Sixty percent (58/97 of the stepwise routines also did not specify the algorithm and/or significance levels. Conclusions The variable selection methods reported in the two journals were limited in variety, and details were often missing. Many studies still relied on problematic techniques like stepwise procedures and/or multiple testing of bivariate associations at the 0.05 alpha-level. These deficiencies should be rectified to safeguard the scientific validity of articles published in Chinese epidemiology journals.

  8. Robust best linear estimation for regression analysis using surrogate and instrumental variables.

    Science.gov (United States)

    Wang, C Y

    2012-04-01

    We investigate methods for regression analysis when covariates are measured with errors. In a subset of the whole cohort, a surrogate variable is available for the true unobserved exposure variable. The surrogate variable satisfies the classical measurement error model, but it may not have repeated measurements. In addition to the surrogate variables that are available among the subjects in the calibration sample, we assume that there is an instrumental variable (IV) that is available for all study subjects. An IV is correlated with the unobserved true exposure variable and hence can be useful in the estimation of the regression coefficients. We propose a robust best linear estimator that uses all the available data, which is the most efficient among a class of consistent estimators. The proposed estimator is shown to be consistent and asymptotically normal under very weak distributional assumptions. For Poisson or linear regression, the proposed estimator is consistent even if the measurement error from the surrogate or IV is heteroscedastic. Finite-sample performance of the proposed estimator is examined and compared with other estimators via intensive simulation studies. The proposed method and other methods are applied to a bladder cancer case-control study.

  9. Novel Harmonic Regularization Approach for Variable Selection in Cox’s Proportional Hazards Model

    Directory of Open Access Journals (Sweden)

    Ge-Jin Chu

    2014-01-01

    Full Text Available Variable selection is an important issue in regression and a number of variable selection methods have been proposed involving nonconvex penalty functions. In this paper, we investigate a novel harmonic regularization method, which can approximate nonconvex Lq  (1/2select key risk factors in the Cox’s proportional hazards model using microarray gene expression data. The harmonic regularization method can be efficiently solved using our proposed direct path seeking approach, which can produce solutions that closely approximate those for the convex loss function and the nonconvex regularization. Simulation results based on the artificial datasets and four real microarray gene expression datasets, such as real diffuse large B-cell lymphoma (DCBCL, the lung cancer, and the AML datasets, show that the harmonic regularization method can be more accurate for variable selection than existing Lasso series methods.

  10. bayesQR: A Bayesian Approach to Quantile Regression

    Directory of Open Access Journals (Sweden)

    Dries F. Benoit

    2017-01-01

    Full Text Available After its introduction by Koenker and Basset (1978, quantile regression has become an important and popular tool to investigate the conditional response distribution in regression. The R package bayesQR contains a number of routines to estimate quantile regression parameters using a Bayesian approach based on the asymmetric Laplace distribution. The package contains functions for the typical quantile regression with continuous dependent variable, but also supports quantile regression for binary dependent variables. For both types of dependent variables, an approach to variable selection using the adaptive lasso approach is provided. For the binary quantile regression model, the package also contains a routine that calculates the fitted probabilities for each vector of predictors. In addition, functions for summarizing the results, creating traceplots, posterior histograms and drawing quantile plots are included. This paper starts with a brief overview of the theoretical background of the models used in the bayesQR package. The main part of this paper discusses the computational problems that arise in the implementation of the procedure and illustrates the usefulness of the package through selected examples.

  11. Advanced colorectal neoplasia risk stratification by penalized logistic regression.

    Science.gov (United States)

    Lin, Yunzhi; Yu, Menggang; Wang, Sijian; Chappell, Richard; Imperiale, Thomas F

    2016-08-01

    Colorectal cancer is the second leading cause of death from cancer in the United States. To facilitate the efficiency of colorectal cancer screening, there is a need to stratify risk for colorectal cancer among the 90% of US residents who are considered "average risk." In this article, we investigate such risk stratification rules for advanced colorectal neoplasia (colorectal cancer and advanced, precancerous polyps). We use a recently completed large cohort study of subjects who underwent a first screening colonoscopy. Logistic regression models have been used in the literature to estimate the risk of advanced colorectal neoplasia based on quantifiable risk factors. However, logistic regression may be prone to overfitting and instability in variable selection. Since most of the risk factors in our study have several categories, it was tempting to collapse these categories into fewer risk groups. We propose a penalized logistic regression method that automatically and simultaneously selects variables, groups categories, and estimates their coefficients by penalizing the [Formula: see text]-norm of both the coefficients and their differences. Hence, it encourages sparsity in the categories, i.e. grouping of the categories, and sparsity in the variables, i.e. variable selection. We apply the penalized logistic regression method to our data. The important variables are selected, with close categories simultaneously grouped, by penalized regression models with and without the interactions terms. The models are validated with 10-fold cross-validation. The receiver operating characteristic curves of the penalized regression models dominate the receiver operating characteristic curve of naive logistic regressions, indicating a superior discriminative performance. © The Author(s) 2013.

  12. Sparse reduced-rank regression with covariance estimation

    KAUST Repository

    Chen, Lisha

    2014-12-08

    Improving the predicting performance of the multiple response regression compared with separate linear regressions is a challenging question. On the one hand, it is desirable to seek model parsimony when facing a large number of parameters. On the other hand, for certain applications it is necessary to take into account the general covariance structure for the errors of the regression model. We assume a reduced-rank regression model and work with the likelihood function with general error covariance to achieve both objectives. In addition we propose to select relevant variables for reduced-rank regression by using a sparsity-inducing penalty, and to estimate the error covariance matrix simultaneously by using a similar penalty on the precision matrix. We develop a numerical algorithm to solve the penalized regression problem. In a simulation study and real data analysis, the new method is compared with two recent methods for multivariate regression and exhibits competitive performance in prediction and variable selection.

  13. Sparse reduced-rank regression with covariance estimation

    KAUST Repository

    Chen, Lisha; Huang, Jianhua Z.

    2014-01-01

    Improving the predicting performance of the multiple response regression compared with separate linear regressions is a challenging question. On the one hand, it is desirable to seek model parsimony when facing a large number of parameters. On the other hand, for certain applications it is necessary to take into account the general covariance structure for the errors of the regression model. We assume a reduced-rank regression model and work with the likelihood function with general error covariance to achieve both objectives. In addition we propose to select relevant variables for reduced-rank regression by using a sparsity-inducing penalty, and to estimate the error covariance matrix simultaneously by using a similar penalty on the precision matrix. We develop a numerical algorithm to solve the penalized regression problem. In a simulation study and real data analysis, the new method is compared with two recent methods for multivariate regression and exhibits competitive performance in prediction and variable selection.

  14. Role of regression model selection and station distribution on the estimation of oceanic anthropogenic carbon change by eMLR

    Directory of Open Access Journals (Sweden)

    Y. Plancherel

    2013-07-01

    Full Text Available Quantifying oceanic anthropogenic carbon uptake by monitoring interior dissolved inorganic carbon (DIC concentrations is complicated by the influence of natural variability. The "eMLR method" aims to address this issue by using empirical regression fits of the data instead of the data themselves, inferring the change in anthropogenic carbon in time by difference between predictions generated by the regressions at each time. The advantages of the method are that it provides in principle a means to filter out natural variability, which theoretically becomes the regression residuals, and a way to deal with sparsely and unevenly distributed data. The degree to which these advantages are realized in practice is unclear, however. The ability of the eMLR method to recover the anthropogenic carbon signal is tested here using a global circulation and biogeochemistry model in which the true signal is known. Results show that regression model selection is particularly important when the observational network changes in time. When the observational network is fixed, the likelihood that co-located systematic misfits between the empirical model and the underlying, yet unknown, true model cancel is greater, improving eMLR results. Changing the observational network modifies how the spatio-temporal variance pattern is captured by the respective datasets, resulting in empirical models that are dynamically or regionally inconsistent, leading to systematic errors. In consequence, the use of regression formulae that change in time to represent systematically best-fit models at all times does not guarantee the best estimates of anthropogenic carbon change if the spatial distributions of the stations emphasize hydrographic features differently in time. Other factors, such as a balanced and representative station coverage, vertical continuity of the regression formulae consistent with the hydrographic context and resiliency of the spatial distribution of the residual

  15. The Effect of Latent Binary Variables on the Uncertainty of the Prediction of a Dichotomous Outcome Using Logistic Regression Based Propensity Score Matching.

    Science.gov (United States)

    Szekér, Szabolcs; Vathy-Fogarassy, Ágnes

    2018-01-01

    Logistic regression based propensity score matching is a widely used method in case-control studies to select the individuals of the control group. This method creates a suitable control group if all factors affecting the output variable are known. However, if relevant latent variables exist as well, which are not taken into account during the calculations, the quality of the control group is uncertain. In this paper, we present a statistics-based research in which we try to determine the relationship between the accuracy of the logistic regression model and the uncertainty of the dependent variable of the control group defined by propensity score matching. Our analyses show that there is a linear correlation between the fit of the logistic regression model and the uncertainty of the output variable. In certain cases, a latent binary explanatory variable can result in a relative error of up to 70% in the prediction of the outcome variable. The observed phenomenon calls the attention of analysts to an important point, which must be taken into account when deducting conclusions.

  16. Model selection with multiple regression on distance matrices leads to incorrect inferences.

    Directory of Open Access Journals (Sweden)

    Ryan P Franckowiak

    Full Text Available In landscape genetics, model selection procedures based on Information Theoretic and Bayesian principles have been used with multiple regression on distance matrices (MRM to test the relationship between multiple vectors of pairwise genetic, geographic, and environmental distance. Using Monte Carlo simulations, we examined the ability of model selection criteria based on Akaike's information criterion (AIC, its small-sample correction (AICc, and the Bayesian information criterion (BIC to reliably rank candidate models when applied with MRM while varying the sample size. The results showed a serious problem: all three criteria exhibit a systematic bias toward selecting unnecessarily complex models containing spurious random variables and erroneously suggest a high level of support for the incorrectly ranked best model. These problems effectively increased with increasing sample size. The failure of AIC, AICc, and BIC was likely driven by the inflated sample size and different sum-of-squares partitioned by MRM, and the resulting effect on delta values. Based on these findings, we strongly discourage the continued application of AIC, AICc, and BIC for model selection with MRM.

  17. A modification of the successive projections algorithm for spectral variable selection in the presence of unknown interferents.

    Science.gov (United States)

    Soares, Sófacles Figueredo Carreiro; Galvão, Roberto Kawakami Harrop; Araújo, Mário César Ugulino; da Silva, Edvan Cirino; Pereira, Claudete Fernandes; de Andrade, Stéfani Iury Evangelista; Leite, Flaviano Carvalho

    2011-03-09

    This work proposes a modification to the successive projections algorithm (SPA) aimed at selecting spectral variables for multiple linear regression (MLR) in the presence of unknown interferents not included in the calibration data set. The modified algorithm favours the selection of variables in which the effect of the interferent is less pronounced. The proposed procedure can be regarded as an adaptive modelling technique, because the spectral features of the samples to be analyzed are considered in the variable selection process. The advantages of this new approach are demonstrated in two analytical problems, namely (1) ultraviolet-visible spectrometric determination of tartrazine, allure red and sunset yellow in aqueous solutions under the interference of erythrosine, and (2) near-infrared spectrometric determination of ethanol in gasoline under the interference of toluene. In these case studies, the performance of conventional MLR-SPA models is substantially degraded by the presence of the interferent. This problem is circumvented by applying the proposed Adaptive MLR-SPA approach, which results in prediction errors smaller than those obtained by three other multivariate calibration techniques, namely stepwise regression, full-spectrum partial-least-squares (PLS) and PLS with variables selected by a genetic algorithm. An inspection of the variable selection results reveals that the Adaptive approach successfully avoids spectral regions in which the interference is more intense. Copyright © 2011 Elsevier B.V. All rights reserved.

  18. SELECTING QUASARS BY THEIR INTRINSIC VARIABILITY

    International Nuclear Information System (INIS)

    Schmidt, Kasper B.; Rix, Hans-Walter; Jester, Sebastian; Hennawi, Joseph F.; Marshall, Philip J.; Dobler, Gregory

    2010-01-01

    We present a new and simple technique for selecting extensive, complete, and pure quasar samples, based on their intrinsic variability. We parameterize the single-band variability by a power-law model for the light-curve structure function, with amplitude A and power-law index γ. We show that quasars can be efficiently separated from other non-variable and variable sources by the location of the individual sources in the A-γ plane. We use ∼60 epochs of imaging data, taken over ∼5 years, from the SDSS stripe 82 (S82) survey, where extensive spectroscopy provides a reference sample of quasars, to demonstrate the power of variability as a quasar classifier in multi-epoch surveys. For UV-excess selected objects, variability performs just as well as the standard SDSS color selection, identifying quasars with a completeness of 90% and a purity of 95%. In the redshift range 2.5 < z < 3, where color selection is known to be problematic, variability can select quasars with a completeness of 90% and a purity of 96%. This is a factor of 5-10 times more pure than existing color selection of quasars in this redshift range. Selecting objects from a broad griz color box without u-band information, variability selection in S82 can afford completeness and purity of 92%, despite a factor of 30 more contaminants than quasars in the color-selected feeder sample. This confirms that the fraction of quasars hidden in the 'stellar locus' of color space is small. To test variability selection in the context of Pan-STARRS 1 (PS1) we created mock PS1 data by down-sampling the S82 data to just six epochs over 3 years. Even with this much sparser time sampling, variability is an encouragingly efficient classifier. For instance, a 92% pure and 44% complete quasar candidate sample is attainable from the above griz-selected catalog. Finally, we show that the presented A-γ technique, besides selecting clean and pure samples of quasars (which are stochastically varying objects), is also

  19. Interpreting Multiple Linear Regression: A Guidebook of Variable Importance

    Science.gov (United States)

    Nathans, Laura L.; Oswald, Frederick L.; Nimon, Kim

    2012-01-01

    Multiple regression (MR) analyses are commonly employed in social science fields. It is also common for interpretation of results to typically reflect overreliance on beta weights, often resulting in very limited interpretations of variable importance. It appears that few researchers employ other methods to obtain a fuller understanding of what…

  20. Surface Estimation, Variable Selection, and the Nonparametric Oracle Property.

    Science.gov (United States)

    Storlie, Curtis B; Bondell, Howard D; Reich, Brian J; Zhang, Hao Helen

    2011-04-01

    Variable selection for multivariate nonparametric regression is an important, yet challenging, problem due, in part, to the infinite dimensionality of the function space. An ideal selection procedure should be automatic, stable, easy to use, and have desirable asymptotic properties. In particular, we define a selection procedure to be nonparametric oracle (np-oracle) if it consistently selects the correct subset of predictors and at the same time estimates the smooth surface at the optimal nonparametric rate, as the sample size goes to infinity. In this paper, we propose a model selection procedure for nonparametric models, and explore the conditions under which the new method enjoys the aforementioned properties. Developed in the framework of smoothing spline ANOVA, our estimator is obtained via solving a regularization problem with a novel adaptive penalty on the sum of functional component norms. Theoretical properties of the new estimator are established. Additionally, numerous simulated and real examples further demonstrate that the new approach substantially outperforms other existing methods in the finite sample setting.

  1. Modified Regression Correlation Coefficient for Poisson Regression Model

    Science.gov (United States)

    Kaengthong, Nattacha; Domthong, Uthumporn

    2017-09-01

    This study gives attention to indicators in predictive power of the Generalized Linear Model (GLM) which are widely used; however, often having some restrictions. We are interested in regression correlation coefficient for a Poisson regression model. This is a measure of predictive power, and defined by the relationship between the dependent variable (Y) and the expected value of the dependent variable given the independent variables [E(Y|X)] for the Poisson regression model. The dependent variable is distributed as Poisson. The purpose of this research was modifying regression correlation coefficient for Poisson regression model. We also compare the proposed modified regression correlation coefficient with the traditional regression correlation coefficient in the case of two or more independent variables, and having multicollinearity in independent variables. The result shows that the proposed regression correlation coefficient is better than the traditional regression correlation coefficient based on Bias and the Root Mean Square Error (RMSE).

  2. A QSAR Study of Environmental Estrogens Based on a Novel Variable Selection Method

    Directory of Open Access Journals (Sweden)

    Aiqian Zhang

    2012-05-01

    Full Text Available A large number of descriptors were employed to characterize the molecular structure of 53 natural, synthetic, and environmental chemicals which are suspected of disrupting endocrine functions by mimicking or antagonizing natural hormones and may thus pose a serious threat to the health of humans and wildlife. In this work, a robust quantitative structure-activity relationship (QSAR model with a novel variable selection method has been proposed for the effective estrogens. The variable selection method is based on variable interaction (VSMVI with leave-multiple-out cross validation (LMOCV to select the best subset. During variable selection, model construction and assessment, the Organization for Economic Co-operation and Development (OECD principles for regulation of QSAR acceptability were fully considered, such as using an unambiguous multiple-linear regression (MLR algorithm to build the model, using several validation methods to assessment the performance of the model, giving the define of applicability domain and analyzing the outliers with the results of molecular docking. The performance of the QSAR model indicates that the VSMVI is an effective, feasible and practical tool for rapid screening of the best subset from large molecular descriptors.

  3. Variable selection in PLSR and extensions to a multi-block setting for metabolomics data

    DEFF Research Database (Denmark)

    Karaman, İbrahim; Hedemann, Mette Skou; Knudsen, Knud Erik Bach

    When applying LC-MS or NMR spectroscopy in metabolomics studies, high-dimensional data are generated and effective tools for variable selection are needed in order to detect the important metabolites. Methods based on sparsity combined with PLSR have recently attracted attention in the field...... of genomics [1]. They became quickly well established in the field of statistics because a close relationship to elastic net has been established. In sparse variable selection combined with PLSR, a soft thresholding is applied on each loading weight separately. In the field of chemometrics Jack-knifing has...... been introduced for variable selection in PLSR [2]. Jack-knifing has been frequently applied in the field of spectroscopy and is implemented in software tools like The Unscrambler. In Jack-knifing uncertainty estimates of regression coefficients are estimated and a t-test is applied on these estimates...

  4. Prediction-Oriented Marker Selection (PROMISE): With Application to High-Dimensional Regression.

    Science.gov (United States)

    Kim, Soyeon; Baladandayuthapani, Veerabhadran; Lee, J Jack

    2017-06-01

    In personalized medicine, biomarkers are used to select therapies with the highest likelihood of success based on an individual patient's biomarker/genomic profile. Two goals are to choose important biomarkers that accurately predict treatment outcomes and to cull unimportant biomarkers to reduce the cost of biological and clinical verifications. These goals are challenging due to the high dimensionality of genomic data. Variable selection methods based on penalized regression (e.g., the lasso and elastic net) have yielded promising results. However, selecting the right amount of penalization is critical to simultaneously achieving these two goals. Standard approaches based on cross-validation (CV) typically provide high prediction accuracy with high true positive rates but at the cost of too many false positives. Alternatively, stability selection (SS) controls the number of false positives, but at the cost of yielding too few true positives. To circumvent these issues, we propose prediction-oriented marker selection (PROMISE), which combines SS with CV to conflate the advantages of both methods. Our application of PROMISE with the lasso and elastic net in data analysis shows that, compared to CV, PROMISE produces sparse solutions, few false positives, and small type I + type II error, and maintains good prediction accuracy, with a marginal decrease in the true positive rates. Compared to SS, PROMISE offers better prediction accuracy and true positive rates. In summary, PROMISE can be applied in many fields to select regularization parameters when the goals are to minimize false positives and maximize prediction accuracy.

  5. Genome-wide prediction of traits with different genetic architecture through efficient variable selection.

    Science.gov (United States)

    Wimmer, Valentin; Lehermeier, Christina; Albrecht, Theresa; Auinger, Hans-Jürgen; Wang, Yu; Schön, Chris-Carolin

    2013-10-01

    In genome-based prediction there is considerable uncertainty about the statistical model and method required to maximize prediction accuracy. For traits influenced by a small number of quantitative trait loci (QTL), predictions are expected to benefit from methods performing variable selection [e.g., BayesB or the least absolute shrinkage and selection operator (LASSO)] compared to methods distributing effects across the genome [ridge regression best linear unbiased prediction (RR-BLUP)]. We investigate the assumptions underlying successful variable selection by combining computer simulations with large-scale experimental data sets from rice (Oryza sativa L.), wheat (Triticum aestivum L.), and Arabidopsis thaliana (L.). We demonstrate that variable selection can be successful when the number of phenotyped individuals is much larger than the number of causal mutations contributing to the trait. We show that the sample size required for efficient variable selection increases dramatically with decreasing trait heritabilities and increasing extent of linkage disequilibrium (LD). We contrast and discuss contradictory results from simulation and experimental studies with respect to superiority of variable selection methods over RR-BLUP. Our results demonstrate that due to long-range LD, medium heritabilities, and small sample sizes, superiority of variable selection methods cannot be expected in plant breeding populations even for traits like FRIGIDA gene expression in Arabidopsis and flowering time in rice, assumed to be influenced by a few major QTL. We extend our conclusions to the analysis of whole-genome sequence data and infer upper bounds for the number of causal mutations which can be identified by LASSO. Our results have major impact on the choice of statistical method needed to make credible inferences about genetic architecture and prediction accuracy of complex traits.

  6. Statistical approach for selection of regression model during validation of bioanalytical method

    Directory of Open Access Journals (Sweden)

    Natalija Nakov

    2014-06-01

    Full Text Available The selection of an adequate regression model is the basis for obtaining accurate and reproducible results during the bionalytical method validation. Given the wide concentration range, frequently present in bioanalytical assays, heteroscedasticity of the data may be expected. Several weighted linear and quadratic regression models were evaluated during the selection of the adequate curve fit using nonparametric statistical tests: One sample rank test and Wilcoxon signed rank test for two independent groups of samples. The results obtained with One sample rank test could not give statistical justification for the selection of linear vs. quadratic regression models because slight differences between the error (presented through the relative residuals were obtained. Estimation of the significance of the differences in the RR was achieved using Wilcoxon signed rank test, where linear and quadratic regression models were treated as two independent groups. The application of this simple non-parametric statistical test provides statistical confirmation of the choice of an adequate regression model.

  7. Effects of environmental variables on invasive amphibian activity: Using model selection on quantiles for counts

    Science.gov (United States)

    Muller, Benjamin J.; Cade, Brian S.; Schwarzkoph, Lin

    2018-01-01

    Many different factors influence animal activity. Often, the value of an environmental variable may influence significantly the upper or lower tails of the activity distribution. For describing relationships with heterogeneous boundaries, quantile regressions predict a quantile of the conditional distribution of the dependent variable. A quantile count model extends linear quantile regression methods to discrete response variables, and is useful if activity is quantified by trapping, where there may be many tied (equal) values in the activity distribution, over a small range of discrete values. Additionally, different environmental variables in combination may have synergistic or antagonistic effects on activity, so examining their effects together, in a modeling framework, is a useful approach. Thus, model selection on quantile counts can be used to determine the relative importance of different variables in determining activity, across the entire distribution of capture results. We conducted model selection on quantile count models to describe the factors affecting activity (numbers of captures) of cane toads (Rhinella marina) in response to several environmental variables (humidity, temperature, rainfall, wind speed, and moon luminosity) over eleven months of trapping. Environmental effects on activity are understudied in this pest animal. In the dry season, model selection on quantile count models suggested that rainfall positively affected activity, especially near the lower tails of the activity distribution. In the wet season, wind speed limited activity near the maximum of the distribution, while minimum activity increased with minimum temperature. This statistical methodology allowed us to explore, in depth, how environmental factors influenced activity across the entire distribution, and is applicable to any survey or trapping regime, in which environmental variables affect activity.

  8. Using variable combination population analysis for variable selection in multivariate calibration.

    Science.gov (United States)

    Yun, Yong-Huan; Wang, Wei-Ting; Deng, Bai-Chuan; Lai, Guang-Bi; Liu, Xin-bo; Ren, Da-Bing; Liang, Yi-Zeng; Fan, Wei; Xu, Qing-Song

    2015-03-03

    Variable (wavelength or feature) selection techniques have become a critical step for the analysis of datasets with high number of variables and relatively few samples. In this study, a novel variable selection strategy, variable combination population analysis (VCPA), was proposed. This strategy consists of two crucial procedures. First, the exponentially decreasing function (EDF), which is the simple and effective principle of 'survival of the fittest' from Darwin's natural evolution theory, is employed to determine the number of variables to keep and continuously shrink the variable space. Second, in each EDF run, binary matrix sampling (BMS) strategy that gives each variable the same chance to be selected and generates different variable combinations, is used to produce a population of subsets to construct a population of sub-models. Then, model population analysis (MPA) is employed to find the variable subsets with the lower root mean squares error of cross validation (RMSECV). The frequency of each variable appearing in the best 10% sub-models is computed. The higher the frequency is, the more important the variable is. The performance of the proposed procedure was investigated using three real NIR datasets. The results indicate that VCPA is a good variable selection strategy when compared with four high performing variable selection methods: genetic algorithm-partial least squares (GA-PLS), Monte Carlo uninformative variable elimination by PLS (MC-UVE-PLS), competitive adaptive reweighted sampling (CARS) and iteratively retains informative variables (IRIV). The MATLAB source code of VCPA is available for academic research on the website: http://www.mathworks.com/matlabcentral/fileexchange/authors/498750. Copyright © 2015 Elsevier B.V. All rights reserved.

  9. gamboostLSS: An R Package for Model Building and Variable Selection in the GAMLSS Framework

    OpenAIRE

    Hofner, Benjamin; Mayr, Andreas; Schmid, Matthias

    2014-01-01

    Generalized additive models for location, scale and shape are a flexible class of regression models that allow to model multiple parameters of a distribution function, such as the mean and the standard deviation, simultaneously. With the R package gamboostLSS, we provide a boosting method to fit these models. Variable selection and model choice are naturally available within this regularized regression framework. To introduce and illustrate the R package gamboostLSS and its infrastructure, we...

  10. Massively-parallel best subset selection for ordinary least-squares regression

    DEFF Research Database (Denmark)

    Gieseke, Fabian; Polsterer, Kai Lars; Mahabal, Ashish

    2017-01-01

    Selecting an optimal subset of k out of d features for linear regression models given n training instances is often considered intractable for feature spaces with hundreds or thousands of dimensions. We propose an efficient massively-parallel implementation for selecting such optimal feature...

  11. Linear regression

    CERN Document Server

    Olive, David J

    2017-01-01

    This text covers both multiple linear regression and some experimental design models. The text uses the response plot to visualize the model and to detect outliers, does not assume that the error distribution has a known parametric distribution, develops prediction intervals that work when the error distribution is unknown, suggests bootstrap hypothesis tests that may be useful for inference after variable selection, and develops prediction regions and large sample theory for the multivariate linear regression model that has m response variables. A relationship between multivariate prediction regions and confidence regions provides a simple way to bootstrap confidence regions. These confidence regions often provide a practical method for testing hypotheses. There is also a chapter on generalized linear models and generalized additive models. There are many R functions to produce response and residual plots, to simulate prediction intervals and hypothesis tests, to detect outliers, and to choose response trans...

  12. Multicollinearity and Regression Analysis

    Science.gov (United States)

    Daoud, Jamal I.

    2017-12-01

    In regression analysis it is obvious to have a correlation between the response and predictor(s), but having correlation among predictors is something undesired. The number of predictors included in the regression model depends on many factors among which, historical data, experience, etc. At the end selection of most important predictors is something objective due to the researcher. Multicollinearity is a phenomena when two or more predictors are correlated, if this happens, the standard error of the coefficients will increase [8]. Increased standard errors means that the coefficients for some or all independent variables may be found to be significantly different from In other words, by overinflating the standard errors, multicollinearity makes some variables statistically insignificant when they should be significant. In this paper we focus on the multicollinearity, reasons and consequences on the reliability of the regression model.

  13. Variable selection by lasso-type methods

    Directory of Open Access Journals (Sweden)

    Sohail Chand

    2011-09-01

    Full Text Available Variable selection is an important property of shrinkage methods. The adaptive lasso is an oracle procedure and can do consistent variable selection. In this paper, we provide an explanation that how use of adaptive weights make it possible for the adaptive lasso to satisfy the necessary and almost sufcient condition for consistent variable selection. We suggest a novel algorithm and give an important result that for the adaptive lasso if predictors are normalised after the introduction of adaptive weights, it makes the adaptive lasso performance identical to the lasso.

  14. Introduction to statistical modelling 2: categorical variables and interactions in linear regression.

    Science.gov (United States)

    Lunt, Mark

    2015-07-01

    In the first article in this series we explored the use of linear regression to predict an outcome variable from a number of predictive factors. It assumed that the predictive factors were measured on an interval scale. However, this article shows how categorical variables can also be included in a linear regression model, enabling predictions to be made separately for different groups and allowing for testing the hypothesis that the outcome differs between groups. The use of interaction terms to measure whether the effect of a particular predictor variable differs between groups is also explained. An alternative approach to testing the difference between groups of the effect of a given predictor, which consists of measuring the effect in each group separately and seeing whether the statistical significance differs between the groups, is shown to be misleading. © The Author 2013. Published by Oxford University Press on behalf of the British Society for Rheumatology. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

  15. Advanced statistics: linear regression, part I: simple linear regression.

    Science.gov (United States)

    Marill, Keith A

    2004-01-01

    Simple linear regression is a mathematical technique used to model the relationship between a single independent predictor variable and a single dependent outcome variable. In this, the first of a two-part series exploring concepts in linear regression analysis, the four fundamental assumptions and the mechanics of simple linear regression are reviewed. The most common technique used to derive the regression line, the method of least squares, is described. The reader will be acquainted with other important concepts in simple linear regression, including: variable transformations, dummy variables, relationship to inference testing, and leverage. Simplified clinical examples with small datasets and graphic models are used to illustrate the points. This will provide a foundation for the second article in this series: a discussion of multiple linear regression, in which there are multiple predictor variables.

  16. A Spline-Based Lack-Of-Fit Test for Independent Variable Effect in Poisson Regression.

    Science.gov (United States)

    Li, Chin-Shang; Tu, Wanzhu

    2007-05-01

    In regression analysis of count data, independent variables are often modeled by their linear effects under the assumption of log-linearity. In reality, the validity of such an assumption is rarely tested, and its use is at times unjustifiable. A lack-of-fit test is proposed for the adequacy of a postulated functional form of an independent variable within the framework of semiparametric Poisson regression models based on penalized splines. It offers added flexibility in accommodating the potentially non-loglinear effect of the independent variable. A likelihood ratio test is constructed for the adequacy of the postulated parametric form, for example log-linearity, of the independent variable effect. Simulations indicate that the proposed model performs well, and misspecified parametric model has much reduced power. An example is given.

  17. Continuous-variable quantum Gaussian process regression and quantum singular value decomposition of nonsparse low-rank matrices

    Science.gov (United States)

    Das, Siddhartha; Siopsis, George; Weedbrook, Christian

    2018-02-01

    With the significant advancement in quantum computation during the past couple of decades, the exploration of machine-learning subroutines using quantum strategies has become increasingly popular. Gaussian process regression is a widely used technique in supervised classical machine learning. Here we introduce an algorithm for Gaussian process regression using continuous-variable quantum systems that can be realized with technology based on photonic quantum computers under certain assumptions regarding distribution of data and availability of efficient quantum access. Our algorithm shows that by using a continuous-variable quantum computer a dramatic speedup in computing Gaussian process regression can be achieved, i.e., the possibility of exponentially reducing the time to compute. Furthermore, our results also include a continuous-variable quantum-assisted singular value decomposition method of nonsparse low rank matrices and forms an important subroutine in our Gaussian process regression algorithm.

  18. Laser-induced Breakdown spectroscopy quantitative analysis method via adaptive analytical line selection and relevance vector machine regression model

    International Nuclear Information System (INIS)

    Yang, Jianhong; Yi, Cancan; Xu, Jinwu; Ma, Xianghong

    2015-01-01

    A new LIBS quantitative analysis method based on analytical line adaptive selection and Relevance Vector Machine (RVM) regression model is proposed. First, a scheme of adaptively selecting analytical line is put forward in order to overcome the drawback of high dependency on a priori knowledge. The candidate analytical lines are automatically selected based on the built-in characteristics of spectral lines, such as spectral intensity, wavelength and width at half height. The analytical lines which will be used as input variables of regression model are determined adaptively according to the samples for both training and testing. Second, an LIBS quantitative analysis method based on RVM is presented. The intensities of analytical lines and the elemental concentrations of certified standard samples are used to train the RVM regression model. The predicted elemental concentration analysis results will be given with a form of confidence interval of probabilistic distribution, which is helpful for evaluating the uncertainness contained in the measured spectra. Chromium concentration analysis experiments of 23 certified standard high-alloy steel samples have been carried out. The multiple correlation coefficient of the prediction was up to 98.85%, and the average relative error of the prediction was 4.01%. The experiment results showed that the proposed LIBS quantitative analysis method achieved better prediction accuracy and better modeling robustness compared with the methods based on partial least squares regression, artificial neural network and standard support vector machine. - Highlights: • Both training and testing samples are considered for analytical lines selection. • The analytical lines are auto-selected based on the built-in characteristics of spectral lines. • The new method can achieve better prediction accuracy and modeling robustness. • Model predictions are given with confidence interval of probabilistic distribution

  19. Selective principal component regression analysis of fluorescence hyperspectral image to assess aflatoxin contamination in corn

    Science.gov (United States)

    Selective principal component regression analysis (SPCR) uses a subset of the original image bands for principal component transformation and regression. For optimal band selection before the transformation, this paper used genetic algorithms (GA). In this case, the GA process used the regression co...

  20. Avoiding and Correcting Bias in Score-Based Latent Variable Regression with Discrete Manifest Items

    Science.gov (United States)

    Lu, Irene R. R.; Thomas, D. Roland

    2008-01-01

    This article considers models involving a single structural equation with latent explanatory and/or latent dependent variables where discrete items are used to measure the latent variables. Our primary focus is the use of scores as proxies for the latent variables and carrying out ordinary least squares (OLS) regression on such scores to estimate…

  1. Exploratory regression analysis: a tool for selecting models and determining predictor importance.

    Science.gov (United States)

    Braun, Michael T; Oswald, Frederick L

    2011-06-01

    Linear regression analysis is one of the most important tools in a researcher's toolbox for creating and testing predictive models. Although linear regression analysis indicates how strongly a set of predictor variables, taken together, will predict a relevant criterion (i.e., the multiple R), the analysis cannot indicate which predictors are the most important. Although there is no definitive or unambiguous method for establishing predictor variable importance, there are several accepted methods. This article reviews those methods for establishing predictor importance and provides a program (in Excel) for implementing them (available for direct download at http://dl.dropbox.com/u/2480715/ERA.xlsm?dl=1) . The program investigates all 2(p) - 1 submodels and produces several indices of predictor importance. This exploratory approach to linear regression, similar to other exploratory data analysis techniques, has the potential to yield both theoretical and practical benefits.

  2. Ultrahigh-dimensional variable selection method for whole-genome gene-gene interaction analysis

    Directory of Open Access Journals (Sweden)

    Ueki Masao

    2012-05-01

    Full Text Available Abstract Background Genome-wide gene-gene interaction analysis using single nucleotide polymorphisms (SNPs is an attractive way for identification of genetic components that confers susceptibility of human complex diseases. Individual hypothesis testing for SNP-SNP pairs as in common genome-wide association study (GWAS however involves difficulty in setting overall p-value due to complicated correlation structure, namely, the multiple testing problem that causes unacceptable false negative results. A large number of SNP-SNP pairs than sample size, so-called the large p small n problem, precludes simultaneous analysis using multiple regression. The method that overcomes above issues is thus needed. Results We adopt an up-to-date method for ultrahigh-dimensional variable selection termed the sure independence screening (SIS for appropriate handling of numerous number of SNP-SNP interactions by including them as predictor variables in logistic regression. We propose ranking strategy using promising dummy coding methods and following variable selection procedure in the SIS method suitably modified for gene-gene interaction analysis. We also implemented the procedures in a software program, EPISIS, using the cost-effective GPGPU (General-purpose computing on graphics processing units technology. EPISIS can complete exhaustive search for SNP-SNP interactions in standard GWAS dataset within several hours. The proposed method works successfully in simulation experiments and in application to real WTCCC (Wellcome Trust Case–control Consortium data. Conclusions Based on the machine-learning principle, the proposed method gives powerful and flexible genome-wide search for various patterns of gene-gene interaction.

  3. Sensor combination and chemometric variable selection for online monitoring of Streptomyces coelicolor fed-batch cultivations

    DEFF Research Database (Denmark)

    Ödman, Peter; Johansen, C.L.; Olsson, L.

    2010-01-01

    of biomass and substrate (casamino acids) concentrations, respectively. The effect of combination of fluorescence and gas analyzer data as well as of different variable selection methods was investigated. Improved prediction models were obtained by combination of data from the two sensors and by variable......Fed-batch cultivations of Streptomyces coelicolor, producing the antibiotic actinorhodin, were monitored online by multiwavelength fluorescence spectroscopy and off-gas analysis. Partial least squares (PLS), locally weighted regression, and multilinear PLS (N-PLS) models were built for prediction...

  4. r2VIM: A new variable selection method for random forests in genome-wide association studies.

    Science.gov (United States)

    Szymczak, Silke; Holzinger, Emily; Dasgupta, Abhijit; Malley, James D; Molloy, Anne M; Mills, James L; Brody, Lawrence C; Stambolian, Dwight; Bailey-Wilson, Joan E

    2016-01-01

    Machine learning methods and in particular random forests (RFs) are a promising alternative to standard single SNP analyses in genome-wide association studies (GWAS). RFs provide variable importance measures (VIMs) to rank SNPs according to their predictive power. However, in contrast to the established genome-wide significance threshold, no clear criteria exist to determine how many SNPs should be selected for downstream analyses. We propose a new variable selection approach, recurrent relative variable importance measure (r2VIM). Importance values are calculated relative to an observed minimal importance score for several runs of RF and only SNPs with large relative VIMs in all of the runs are selected as important. Evaluations on simulated GWAS data show that the new method controls the number of false-positives under the null hypothesis. Under a simple alternative hypothesis with several independent main effects it is only slightly less powerful than logistic regression. In an experimental GWAS data set, the same strong signal is identified while the approach selects none of the SNPs in an underpowered GWAS. The novel variable selection method r2VIM is a promising extension to standard RF for objectively selecting relevant SNPs in GWAS while controlling the number of false-positive results.

  5. Ultrahigh Dimensional Variable Selection for Interpolation of Point Referenced Spatial Data: A Digital Soil Mapping Case Study

    Science.gov (United States)

    Lamb, David W.; Mengersen, Kerrie

    2016-01-01

    Modern soil mapping is characterised by the need to interpolate point referenced (geostatistical) observations and the availability of large numbers of environmental characteristics for consideration as covariates to aid this interpolation. Modelling tasks of this nature also occur in other fields such as biogeography and environmental science. This analysis employs the Least Angle Regression (LAR) algorithm for fitting Least Absolute Shrinkage and Selection Operator (LASSO) penalized Multiple Linear Regressions models. This analysis demonstrates the efficiency of the LAR algorithm at selecting covariates to aid the interpolation of geostatistical soil carbon observations. Where an exhaustive search of the models that could be constructed from 800 potential covariate terms and 60 observations would be prohibitively demanding, LASSO variable selection is accomplished with trivial computational investment. PMID:27603135

  6. Effects of categorization method, regression type, and variable distribution on the inflation of Type-I error rate when categorizing a confounding variable.

    Science.gov (United States)

    Barnwell-Ménard, Jean-Louis; Li, Qing; Cohen, Alan A

    2015-03-15

    The loss of signal associated with categorizing a continuous variable is well known, and previous studies have demonstrated that this can lead to an inflation of Type-I error when the categorized variable is a confounder in a regression analysis estimating the effect of an exposure on an outcome. However, it is not known how the Type-I error may vary under different circumstances, including logistic versus linear regression, different distributions of the confounder, and different categorization methods. Here, we analytically quantified the effect of categorization and then performed a series of 9600 Monte Carlo simulations to estimate the Type-I error inflation associated with categorization of a confounder under different regression scenarios. We show that Type-I error is unacceptably high (>10% in most scenarios and often 100%). The only exception was when the variable categorized was a continuous mixture proxy for a genuinely dichotomous latent variable, where both the continuous proxy and the categorized variable are error-ridden proxies for the dichotomous latent variable. As expected, error inflation was also higher with larger sample size, fewer categories, and stronger associations between the confounder and the exposure or outcome. We provide online tools that can help researchers estimate the potential error inflation and understand how serious a problem this is. Copyright © 2014 John Wiley & Sons, Ltd.

  7. JT-60 configuration parameters for feedback control determined by regression analysis

    Energy Technology Data Exchange (ETDEWEB)

    Matsukawa, Makoto; Hosogane, Nobuyuki; Ninomiya, Hiromasa (Japan Atomic Energy Research Inst., Naka, Ibaraki (Japan). Naka Fusion Research Establishment)

    1991-12-01

    The stepwise regression procedure was applied to obtain measurement formulas for equilibrium parameters used in the feedback control of JT-60. This procedure automatically selects variables necessary for the measurements, and selects a set of variables which are not likely to be picked up by physical considerations. Regression equations with stable and small multicollinearity were obtained and it was experimentally confirmed that the measurement formulas obtained through this procedure were accurate enough to be applicable to the feedback control of plasma configurations in JT-60. (author).

  8. JT-60 configuration parameters for feedback control determined by regression analysis

    International Nuclear Information System (INIS)

    Matsukawa, Makoto; Hosogane, Nobuyuki; Ninomiya, Hiromasa

    1991-12-01

    The stepwise regression procedure was applied to obtain measurement formulas for equilibrium parameters used in the feedback control of JT-60. This procedure automatically selects variables necessary for the measurements, and selects a set of variables which are not likely to be picked up by physical considerations. Regression equations with stable and small multicollinearity were obtained and it was experimentally confirmed that the measurement formulas obtained through this procedure were accurate enough to be applicable to the feedback control of plasma configurations in JT-60. (author)

  9. Uncovering state-dependent relationships in shallow lakes using Bayesian latent variable regression.

    Science.gov (United States)

    Vitense, Kelsey; Hanson, Mark A; Herwig, Brian R; Zimmer, Kyle D; Fieberg, John

    2018-03-01

    Ecosystems sometimes undergo dramatic shifts between contrasting regimes. Shallow lakes, for instance, can transition between two alternative stable states: a clear state dominated by submerged aquatic vegetation and a turbid state dominated by phytoplankton. Theoretical models suggest that critical nutrient thresholds differentiate three lake types: highly resilient clear lakes, lakes that may switch between clear and turbid states following perturbations, and highly resilient turbid lakes. For effective and efficient management of shallow lakes and other systems, managers need tools to identify critical thresholds and state-dependent relationships between driving variables and key system features. Using shallow lakes as a model system for which alternative stable states have been demonstrated, we developed an integrated framework using Bayesian latent variable regression (BLR) to classify lake states, identify critical total phosphorus (TP) thresholds, and estimate steady state relationships between TP and chlorophyll a (chl a) using cross-sectional data. We evaluated the method using data simulated from a stochastic differential equation model and compared its performance to k-means clustering with regression (KMR). We also applied the framework to data comprising 130 shallow lakes. For simulated data sets, BLR had high state classification rates (median/mean accuracy >97%) and accurately estimated TP thresholds and state-dependent TP-chl a relationships. Classification and estimation improved with increasing sample size and decreasing noise levels. Compared to KMR, BLR had higher classification rates and better approximated the TP-chl a steady state relationships and TP thresholds. We fit the BLR model to three different years of empirical shallow lake data, and managers can use the estimated bifurcation diagrams to prioritize lakes for management according to their proximity to thresholds and chance of successful rehabilitation. Our model improves upon

  10. Logistic regression applied to natural hazards: rare event logistic regression with replications

    Science.gov (United States)

    Guns, M.; Vanacker, V.

    2012-06-01

    Statistical analysis of natural hazards needs particular attention, as most of these phenomena are rare events. This study shows that the ordinary rare event logistic regression, as it is now commonly used in geomorphologic studies, does not always lead to a robust detection of controlling factors, as the results can be strongly sample-dependent. In this paper, we introduce some concepts of Monte Carlo simulations in rare event logistic regression. This technique, so-called rare event logistic regression with replications, combines the strength of probabilistic and statistical methods, and allows overcoming some of the limitations of previous developments through robust variable selection. This technique was here developed for the analyses of landslide controlling factors, but the concept is widely applicable for statistical analyses of natural hazards.

  11. A novel relational regularization feature selection method for joint regression and classification in AD diagnosis.

    Science.gov (United States)

    Zhu, Xiaofeng; Suk, Heung-Il; Wang, Li; Lee, Seong-Whan; Shen, Dinggang

    2017-05-01

    In this paper, we focus on joint regression and classification for Alzheimer's disease diagnosis and propose a new feature selection method by embedding the relational information inherent in the observations into a sparse multi-task learning framework. Specifically, the relational information includes three kinds of relationships (such as feature-feature relation, response-response relation, and sample-sample relation), for preserving three kinds of the similarity, such as for the features, the response variables, and the samples, respectively. To conduct feature selection, we first formulate the objective function by imposing these three relational characteristics along with an ℓ 2,1 -norm regularization term, and further propose a computationally efficient algorithm to optimize the proposed objective function. With the dimension-reduced data, we train two support vector regression models to predict the clinical scores of ADAS-Cog and MMSE, respectively, and also a support vector classification model to determine the clinical label. We conducted extensive experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset to validate the effectiveness of the proposed method. Our experimental results showed the efficacy of the proposed method in enhancing the performances of both clinical scores prediction and disease status identification, compared to the state-of-the-art methods. Copyright © 2015 Elsevier B.V. All rights reserved.

  12. Multiresponse semiparametric regression for modelling the effect of regional socio-economic variables on the use of information technology

    Science.gov (United States)

    Wibowo, Wahyu; Wene, Chatrien; Budiantara, I. Nyoman; Permatasari, Erma Oktania

    2017-03-01

    Multiresponse semiparametric regression is simultaneous equation regression model and fusion of parametric and nonparametric model. The regression model comprise several models and each model has two components, parametric and nonparametric. The used model has linear function as parametric and polynomial truncated spline as nonparametric component. The model can handle both linearity and nonlinearity relationship between response and the sets of predictor variables. The aim of this paper is to demonstrate the application of the regression model for modeling of effect of regional socio-economic on use of information technology. More specific, the response variables are percentage of households has access to internet and percentage of households has personal computer. Then, predictor variables are percentage of literacy people, percentage of electrification and percentage of economic growth. Based on identification of the relationship between response and predictor variable, economic growth is treated as nonparametric predictor and the others are parametric predictors. The result shows that the multiresponse semiparametric regression can be applied well as indicate by the high coefficient determination, 90 percent.

  13. Advanced statistics: linear regression, part II: multiple linear regression.

    Science.gov (United States)

    Marill, Keith A

    2004-01-01

    The applications of simple linear regression in medical research are limited, because in most situations, there are multiple relevant predictor variables. Univariate statistical techniques such as simple linear regression use a single predictor variable, and they often may be mathematically correct but clinically misleading. Multiple linear regression is a mathematical technique used to model the relationship between multiple independent predictor variables and a single dependent outcome variable. It is used in medical research to model observational data, as well as in diagnostic and therapeutic studies in which the outcome is dependent on more than one factor. Although the technique generally is limited to data that can be expressed with a linear function, it benefits from a well-developed mathematical framework that yields unique solutions and exact confidence intervals for regression coefficients. Building on Part I of this series, this article acquaints the reader with some of the important concepts in multiple regression analysis. These include multicollinearity, interaction effects, and an expansion of the discussion of inference testing, leverage, and variable transformations to multivariate models. Examples from the first article in this series are expanded on using a primarily graphic, rather than mathematical, approach. The importance of the relationships among the predictor variables and the dependence of the multivariate model coefficients on the choice of these variables are stressed. Finally, concepts in regression model building are discussed.

  14. Estimating severity of sideways fall using a generic multi linear regression model based on kinematic input variables.

    Science.gov (United States)

    van der Zijden, A M; Groen, B E; Tanck, E; Nienhuis, B; Verdonschot, N; Weerdesteyn, V

    2017-03-21

    Many research groups have studied fall impact mechanics to understand how fall severity can be reduced to prevent hip fractures. Yet, direct impact force measurements with force plates are restricted to a very limited repertoire of experimental falls. The purpose of this study was to develop a generic model for estimating hip impact forces (i.e. fall severity) in in vivo sideways falls without the use of force plates. Twelve experienced judokas performed sideways Martial Arts (MA) and Block ('natural') falls on a force plate, both with and without a mat on top. Data were analyzed to determine the hip impact force and to derive 11 selected (subject-specific and kinematic) variables. Falls from kneeling height were used to perform a stepwise regression procedure to assess the effects of these input variables and build the model. The final model includes four input variables, involving one subject-specific measure and three kinematic variables: maximum upper body deceleration, body mass, shoulder angle at the instant of 'maximum impact' and maximum hip deceleration. The results showed that estimated and measured hip impact forces were linearly related (explained variances ranging from 46 to 63%). Hip impact forces of MA falls onto the mat from a standing position (3650±916N) estimated by the final model were comparable with measured values (3698±689N), even though these data were not used for training the model. In conclusion, a generic linear regression model was developed that enables the assessment of fall severity through kinematic measures of sideways falls, without using force plates. Copyright © 2017 Elsevier Ltd. All rights reserved.

  15. Multiple linear regression analysis

    Science.gov (United States)

    Edwards, T. R.

    1980-01-01

    Program rapidly selects best-suited set of coefficients. User supplies only vectors of independent and dependent data and specifies confidence level required. Program uses stepwise statistical procedure for relating minimal set of variables to set of observations; final regression contains only most statistically significant coefficients. Program is written in FORTRAN IV for batch execution and has been implemented on NOVA 1200.

  16. Online Monitoring of Copper Damascene Electroplating Bath by Voltammetry: Selection of Variables for Multiblock and Hierarchical Chemometric Analysis of Voltammetric Data

    Directory of Open Access Journals (Sweden)

    Aleksander Jaworski

    2017-01-01

    Full Text Available The Real Time Analyzer (RTA utilizing DC- and AC-voltammetric techniques is an in situ, online monitoring system that provides a complete chemical analysis of different electrochemical deposition solutions. The RTA employs multivariate calibration when predicting concentration parameters from a multivariate data set. Although the hierarchical and multiblock Principal Component Regression- (PCR- and Partial Least Squares- (PLS- based methods can handle data sets even when the number of variables significantly exceeds the number of samples, it can be advantageous to reduce the number of variables to obtain improvement of the model predictions and better interpretation. This presentation focuses on the introduction of a multistep, rigorous method of data-selection-based Least Squares Regression, Simple Modeling of Class Analogy modeling power, and, as a novel application in electroanalysis, Uninformative Variable Elimination by PLS and by PCR, Variable Importance in the Projection coupled with PLS, Interval PLS, Interval PCR, and Moving Window PLS. Selection criteria of the optimum decomposition technique for the specific data are also demonstrated. The chief goal of this paper is to introduce to the community of electroanalytical chemists numerous variable selection methods which are well established in spectroscopy and can be successfully applied to voltammetric data analysis.

  17. A regression approach for Zircaloy-2 in-reactor creep constitutive equations

    International Nuclear Information System (INIS)

    Yung Liu, Y.; Bement, A.L.

    1977-01-01

    In this paper the methodology of multiple regressions as applied to Zircaloy-2 in-reactor creep data analysis and construction of constitutive equation are illustrated. While the resulting constitutive equation can be used in creep analysis of in-reactor Zircaloy structural components, the methodology itself is entirely general and can be applied to any creep data analysis. The promising aspects of multiple regression creep data analysis are briefly outlined as follows: (1) When there are more than one variable involved, there is no need to make the assumption that each variable affects the response independently. No separate normalizations are required either and the estimation of parameters is obtained by solving many simultaneous equations. The number of simultaneous equations is equal to the number of data sets. (2) Regression statistics such as R 2 - and F-statistics provide measures of the significance of regression creep equation in correlating the overall data. The relative weights of each variable on the response can also be obtained. (3) Special regression techniques such as step-wise, ridge, and robust regressions and residual plots, etc., provide diagnostic tools for model selections. Multiple regression analysis performed on a set of carefully selected Zircaloy-2 in-reactor creep data leads to a model which provides excellent correlations for the data. (Auth.)

  18. Soil Cd, Cr, Cu, Ni, Pb and Zn sorption and retention models using SVM: Variable selection and competitive model.

    Science.gov (United States)

    González Costa, J J; Reigosa, M J; Matías, J M; Covelo, E F

    2017-09-01

    The aim of this study was to model the sorption and retention of Cd, Cu, Ni, Pb and Zn in soils. To that extent, the sorption and retention of these metals were studied and the soil characterization was performed separately. Multiple stepwise regression was used to produce multivariate models with linear techniques and with support vector machines, all of which included 15 explanatory variables characterizing soils. When the R-squared values are represented, two different groups are noticed. Cr, Cu and Pb sorption and retention show a higher R-squared; the most explanatory variables being humified organic matter, Al oxides and, in some cases, cation-exchange capacity (CEC). The other group of metals (Cd, Ni and Zn) shows a lower R-squared, and clays are the most explanatory variables, including a percentage of vermiculite and slime. In some cases, quartz, plagioclase or hematite percentages also show some explanatory capacity. Support Vector Machine (SVM) regression shows that the different models are not as regular as in multiple regression in terms of number of variables, the regression for nickel adsorption being the one with the highest number of variables in its optimal model. On the other hand, there are cases where the most explanatory variables are the same for two metals, as it happens with Cd and Cr adsorption. A similar adsorption mechanism is thus postulated. These patterns of the introduction of variables in the model allow us to create explainability sequences. Those which are the most similar to the selectivity sequences obtained by Covelo (2005) are Mn oxides in multiple regression and change capacity in SVM. Among all the variables, the only one that is explanatory for all the metals after applying the maximum parsimony principle is the percentage of sand in the retention process. In the competitive model arising from the aforementioned sequences, the most intense competitiveness for the adsorption and retention of different metals appears between

  19. Logistic regression applied to natural hazards: rare event logistic regression with replications

    Directory of Open Access Journals (Sweden)

    M. Guns

    2012-06-01

    Full Text Available Statistical analysis of natural hazards needs particular attention, as most of these phenomena are rare events. This study shows that the ordinary rare event logistic regression, as it is now commonly used in geomorphologic studies, does not always lead to a robust detection of controlling factors, as the results can be strongly sample-dependent. In this paper, we introduce some concepts of Monte Carlo simulations in rare event logistic regression. This technique, so-called rare event logistic regression with replications, combines the strength of probabilistic and statistical methods, and allows overcoming some of the limitations of previous developments through robust variable selection. This technique was here developed for the analyses of landslide controlling factors, but the concept is widely applicable for statistical analyses of natural hazards.

  20. The use of cognitive ability measures as explanatory variables in regression analysis.

    Science.gov (United States)

    Junker, Brian; Schofield, Lynne Steuerle; Taylor, Lowell J

    2012-12-01

    Cognitive ability measures are often taken as explanatory variables in regression analysis, e.g., as a factor affecting a market outcome such as an individual's wage, or a decision such as an individual's education acquisition. Cognitive ability is a latent construct; its true value is unobserved. Nonetheless, researchers often assume that a test score , constructed via standard psychometric practice from individuals' responses to test items, can be safely used in regression analysis. We examine problems that can arise, and suggest that an alternative approach, a "mixed effects structural equations" (MESE) model, may be more appropriate in many circumstances.

  1. gamboostLSS: An R Package for Model Building and Variable Selection in the GAMLSS Framework

    Directory of Open Access Journals (Sweden)

    Benjamin Hofner

    2016-10-01

    Full Text Available Generalized additive models for location, scale and shape are a flexible class of regression models that allow to model multiple parameters of a distribution function, such as the mean and the standard deviation, simultaneously. With the R package gamboostLSS, we provide a boosting method to fit these models. Variable selection and model choice are naturally available within this regularized regression framework. To introduce and illustrate the R package gamboostLSS and its infrastructure, we use a data set on stunted growth in India. In addition to the specification and application of the model itself, we present a variety of convenience functions, including methods for tuning parameter selection, prediction and visualization of results. The package gamboostLSS is available from the Comprehensive R Archive Network (CRAN at https://CRAN.R-project.org/package=gamboostLSS.

  2. Parameter Selection Method for Support Vector Regression Based on Adaptive Fusion of the Mixed Kernel Function

    Directory of Open Access Journals (Sweden)

    Hailun Wang

    2017-01-01

    Full Text Available Support vector regression algorithm is widely used in fault diagnosis of rolling bearing. A new model parameter selection method for support vector regression based on adaptive fusion of the mixed kernel function is proposed in this paper. We choose the mixed kernel function as the kernel function of support vector regression. The mixed kernel function of the fusion coefficients, kernel function parameters, and regression parameters are combined together as the parameters of the state vector. Thus, the model selection problem is transformed into a nonlinear system state estimation problem. We use a 5th-degree cubature Kalman filter to estimate the parameters. In this way, we realize the adaptive selection of mixed kernel function weighted coefficients and the kernel parameters, the regression parameters. Compared with a single kernel function, unscented Kalman filter (UKF support vector regression algorithms, and genetic algorithms, the decision regression function obtained by the proposed method has better generalization ability and higher prediction accuracy.

  3. Impact of multicollinearity on small sample hydrologic regression models

    Science.gov (United States)

    Kroll, Charles N.; Song, Peter

    2013-06-01

    Often hydrologic regression models are developed with ordinary least squares (OLS) procedures. The use of OLS with highly correlated explanatory variables produces multicollinearity, which creates highly sensitive parameter estimators with inflated variances and improper model selection. It is not clear how to best address multicollinearity in hydrologic regression models. Here a Monte Carlo simulation is developed to compare four techniques to address multicollinearity: OLS, OLS with variance inflation factor screening (VIF), principal component regression (PCR), and partial least squares regression (PLS). The performance of these four techniques was observed for varying sample sizes, correlation coefficients between the explanatory variables, and model error variances consistent with hydrologic regional regression models. The negative effects of multicollinearity are magnified at smaller sample sizes, higher correlations between the variables, and larger model error variances (smaller R2). The Monte Carlo simulation indicates that if the true model is known, multicollinearity is present, and the estimation and statistical testing of regression parameters are of interest, then PCR or PLS should be employed. If the model is unknown, or if the interest is solely on model predictions, is it recommended that OLS be employed since using more complicated techniques did not produce any improvement in model performance. A leave-one-out cross-validation case study was also performed using low-streamflow data sets from the eastern United States. Results indicate that OLS with stepwise selection generally produces models across study regions with varying levels of multicollinearity that are as good as biased regression techniques such as PCR and PLS.

  4. Variable selection based near infrared spectroscopy quantitative and qualitative analysis on wheat wet gluten

    Science.gov (United States)

    Lü, Chengxu; Jiang, Xunpeng; Zhou, Xingfan; Zhang, Yinqiao; Zhang, Naiqian; Wei, Chongfeng; Mao, Wenhua

    2017-10-01

    Wet gluten is a useful quality indicator for wheat, and short wave near infrared spectroscopy (NIRS) is a high performance technique with the advantage of economic rapid and nondestructive test. To study the feasibility of short wave NIRS analyzing wet gluten directly from wheat seed, 54 representative wheat seed samples were collected and scanned by spectrometer. 8 spectral pretreatment method and genetic algorithm (GA) variable selection method were used to optimize analysis. Both quantitative and qualitative model of wet gluten were built by partial least squares regression and discriminate analysis. For quantitative analysis, normalization is the optimized pretreatment method, 17 wet gluten sensitive variables are selected by GA, and GA model performs a better result than that of all variable model, with R2V=0.88, and RMSEV=1.47. For qualitative analysis, automatic weighted least squares baseline is the optimized pretreatment method, all variable models perform better results than those of GA models. The correct classification rates of 3 class of 30% wet gluten content are 95.45, 84.52, and 90.00%, respectively. The short wave NIRS technique shows potential for both quantitative and qualitative analysis of wet gluten for wheat seed.

  5. Vector regression introduced

    Directory of Open Access Journals (Sweden)

    Mok Tik

    2014-06-01

    Full Text Available This study formulates regression of vector data that will enable statistical analysis of various geodetic phenomena such as, polar motion, ocean currents, typhoon/hurricane tracking, crustal deformations, and precursory earthquake signals. The observed vector variable of an event (dependent vector variable is expressed as a function of a number of hypothesized phenomena realized also as vector variables (independent vector variables and/or scalar variables that are likely to impact the dependent vector variable. The proposed representation has the unique property of solving the coefficients of independent vector variables (explanatory variables also as vectors, hence it supersedes multivariate multiple regression models, in which the unknown coefficients are scalar quantities. For the solution, complex numbers are used to rep- resent vector information, and the method of least squares is deployed to estimate the vector model parameters after transforming the complex vector regression model into a real vector regression model through isomorphism. Various operational statistics for testing the predictive significance of the estimated vector parameter coefficients are also derived. A simple numerical example demonstrates the use of the proposed vector regression analysis in modeling typhoon paths.

  6. Comparison of selected variables of gaming performance in football

    OpenAIRE

    Parachin, Jiří

    2014-01-01

    Title: Comparison of selected variables of gaming performance in football Objectives: Analysis of selected variables of gaming performance in the matches of professional Czech football teams in the Champions League and UEFA Europa League in 2013. During the observation to register set variables, then evaluate obtained results and compare them. Methods: The use of observational analysis and comparison of selected variables of gaming performance in competitive matches of professional football. ...

  7. A Meta-Heuristic Regression-Based Feature Selection for Predictive Analytics

    Directory of Open Access Journals (Sweden)

    Bharat Singh

    2014-11-01

    Full Text Available A high-dimensional feature selection having a very large number of features with an optimal feature subset is an NP-complete problem. Because conventional optimization techniques are unable to tackle large-scale feature selection problems, meta-heuristic algorithms are widely used. In this paper, we propose a particle swarm optimization technique while utilizing regression techniques for feature selection. We then use the selected features to classify the data. Classification accuracy is used as a criterion to evaluate classifier performance, and classification is accomplished through the use of k-nearest neighbour (KNN and Bayesian techniques. Various high dimensional data sets are used to evaluate the usefulness of the proposed approach. Results show that our approach gives better results when compared with other conventional feature selection algorithms.

  8. Model Selection in Kernel Ridge Regression

    DEFF Research Database (Denmark)

    Exterkate, Peter

    Kernel ridge regression is gaining popularity as a data-rich nonlinear forecasting tool, which is applicable in many different contexts. This paper investigates the influence of the choice of kernel and the setting of tuning parameters on forecast accuracy. We review several popular kernels......, including polynomial kernels, the Gaussian kernel, and the Sinc kernel. We interpret the latter two kernels in terms of their smoothing properties, and we relate the tuning parameters associated to all these kernels to smoothness measures of the prediction function and to the signal-to-noise ratio. Based...... on these interpretations, we provide guidelines for selecting the tuning parameters from small grids using cross-validation. A Monte Carlo study confirms the practical usefulness of these rules of thumb. Finally, the flexible and smooth functional forms provided by the Gaussian and Sinc kernels makes them widely...

  9. Methods for identifying SNP interactions: a review on variations of Logic Regression, Random Forest and Bayesian logistic regression.

    Science.gov (United States)

    Chen, Carla Chia-Ming; Schwender, Holger; Keith, Jonathan; Nunkesser, Robin; Mengersen, Kerrie; Macrossan, Paula

    2011-01-01

    Due to advancements in computational ability, enhanced technology and a reduction in the price of genotyping, more data are being generated for understanding genetic associations with diseases and disorders. However, with the availability of large data sets comes the inherent challenges of new methods of statistical analysis and modeling. Considering a complex phenotype may be the effect of a combination of multiple loci, various statistical methods have been developed for identifying genetic epistasis effects. Among these methods, logic regression (LR) is an intriguing approach incorporating tree-like structures. Various methods have built on the original LR to improve different aspects of the model. In this study, we review four variations of LR, namely Logic Feature Selection, Monte Carlo Logic Regression, Genetic Programming for Association Studies, and Modified Logic Regression-Gene Expression Programming, and investigate the performance of each method using simulated and real genotype data. We contrast these with another tree-like approach, namely Random Forests, and a Bayesian logistic regression with stochastic search variable selection.

  10. Robust cluster analysis and variable selection

    CERN Document Server

    Ritter, Gunter

    2014-01-01

    Clustering remains a vibrant area of research in statistics. Although there are many books on this topic, there are relatively few that are well founded in the theoretical aspects. In Robust Cluster Analysis and Variable Selection, Gunter Ritter presents an overview of the theory and applications of probabilistic clustering and variable selection, synthesizing the key research results of the last 50 years. The author focuses on the robust clustering methods he found to be the most useful on simulated data and real-time applications. The book provides clear guidance for the varying needs of bot

  11. ANYOLS, Least Square Fit by Stepwise Regression

    International Nuclear Information System (INIS)

    Atwoods, C.L.; Mathews, S.

    1986-01-01

    Description of program or function: ANYOLS is a stepwise program which fits data using ordinary or weighted least squares. Variables are selected for the model in a stepwise way based on a user- specified input criterion or a user-written subroutine. The order in which variables are entered can be influenced by user-defined forcing priorities. Instead of stepwise selection, ANYOLS can try all possible combinations of any desired subset of the variables. Automatic output for the final model in a stepwise search includes plots of the residuals, 'studentized' residuals, and leverages; if the model is not too large, the output also includes partial regression and partial leverage plots. A data set may be re-used so that several selection criteria can be tried. Flexibility is increased by allowing the substitution of user-written subroutines for several default subroutines

  12. Short-term load forecasting with increment regression tree

    Energy Technology Data Exchange (ETDEWEB)

    Yang, Jingfei; Stenzel, Juergen [Darmstadt University of Techonology, Darmstadt 64283 (Germany)

    2006-06-15

    This paper presents a new regression tree method for short-term load forecasting. Both increment and non-increment tree are built according to the historical data to provide the data space partition and input variable selection. Support vector machine is employed to the samples of regression tree nodes for further fine regression. Results of different tree nodes are integrated through weighted average method to obtain the comprehensive forecasting result. The effectiveness of the proposed method is demonstrated through its application to an actual system. (author)

  13. Polychotomization of continuous variables in regression models based on the overall C index

    Directory of Open Access Journals (Sweden)

    Bax Leon

    2006-12-01

    Full Text Available Abstract Background When developing multivariable regression models for diagnosis or prognosis, continuous independent variables can be categorized to make a prediction table instead of a prediction formula. Although many methods have been proposed to dichotomize prognostic variables, to date there has been no integrated method for polychotomization. The latter is necessary when dichotomization results in too much loss of information or when central values refer to normal states and more dispersed values refer to less preferable states, a situation that is not unusual in medical settings (e.g. body temperature, blood pressure. The goal of our study was to develop a theoretical and practical method for polychotomization. Methods We used the overall discrimination index C, introduced by Harrel, as a measure of the predictive ability of an independent regressor variable and derived a method for polychotomization mathematically. Since the naïve application of our method, like some existing methods, gives rise to positive bias, we developed a parametric method that minimizes this bias and assessed its performance by the use of Monte Carlo simulation. Results The overall C is closely related to the area under the ROC curve and the produced di(polychotomized variable's predictive performance is comparable to the original continuous variable. The simulation shows that the parametric method is essentially unbiased for both the estimates of performance and the cutoff points. Application of our method to the predictor variables of a previous study on rhabdomyolysis shows that it can be used to make probability profile tables that are applicable to the diagnosis or prognosis of individual patient status. Conclusion We propose a polychotomization (including dichotomization method for independent continuous variables in regression models based on the overall discrimination index C and clarified its meaning mathematically. To avoid positive bias in

  14. Straight line fitting and predictions: On a marginal likelihood approach to linear regression and errors-in-variables models

    Science.gov (United States)

    Christiansen, Bo

    2015-04-01

    Linear regression methods are without doubt the most used approaches to describe and predict data in the physical sciences. They are often good first order approximations and they are in general easier to apply and interpret than more advanced methods. However, even the properties of univariate regression can lead to debate over the appropriateness of various models as witnessed by the recent discussion about climate reconstruction methods. Before linear regression is applied important choices have to be made regarding the origins of the noise terms and regarding which of the two variables under consideration that should be treated as the independent variable. These decisions are often not easy to make but they may have a considerable impact on the results. We seek to give a unified probabilistic - Bayesian with flat priors - treatment of univariate linear regression and prediction by taking, as starting point, the general errors-in-variables model (Christiansen, J. Clim., 27, 2014-2031, 2014). Other versions of linear regression can be obtained as limits of this model. We derive the likelihood of the model parameters and predictands of the general errors-in-variables model by marginalizing over the nuisance parameters. The resulting likelihood is relatively simple and easy to analyze and calculate. The well known unidentifiability of the errors-in-variables model is manifested as the absence of a well-defined maximum in the likelihood. However, this does not mean that probabilistic inference can not be made; the marginal likelihoods of model parameters and the predictands have, in general, well-defined maxima. We also include a probabilistic version of classical calibration and show how it is related to the errors-in-variables model. The results are illustrated by an example from the coupling between the lower stratosphere and the troposphere in the Northern Hemisphere winter.

  15. A Poisson regression approach to model monthly hail occurrence in Northern Switzerland using large-scale environmental variables

    Science.gov (United States)

    Madonna, Erica; Ginsbourger, David; Martius, Olivia

    2018-05-01

    In Switzerland, hail regularly causes substantial damage to agriculture, cars and infrastructure, however, little is known about its long-term variability. To study the variability, the monthly number of days with hail in northern Switzerland is modeled in a regression framework using large-scale predictors derived from ERA-Interim reanalysis. The model is developed and verified using radar-based hail observations for the extended summer season (April-September) in the period 2002-2014. The seasonality of hail is explicitly modeled with a categorical predictor (month) and monthly anomalies of several large-scale predictors are used to capture the year-to-year variability. Several regression models are applied and their performance tested with respect to standard scores and cross-validation. The chosen model includes four predictors: the monthly anomaly of the two meter temperature, the monthly anomaly of the logarithm of the convective available potential energy (CAPE), the monthly anomaly of the wind shear and the month. This model well captures the intra-annual variability and slightly underestimates its inter-annual variability. The regression model is applied to the reanalysis data back in time to 1980. The resulting hail day time series shows an increase of the number of hail days per month, which is (in the model) related to an increase in temperature and CAPE. The trend corresponds to approximately 0.5 days per month per decade. The results of the regression model have been compared to two independent data sets. All data sets agree on the sign of the trend, but the trend is weaker in the other data sets.

  16. Ordinary least square regression, orthogonal regression, geometric mean regression and their applications in aerosol science

    International Nuclear Information System (INIS)

    Leng Ling; Zhang Tianyi; Kleinman, Lawrence; Zhu Wei

    2007-01-01

    Regression analysis, especially the ordinary least squares method which assumes that errors are confined to the dependent variable, has seen a fair share of its applications in aerosol science. The ordinary least squares approach, however, could be problematic due to the fact that atmospheric data often does not lend itself to calling one variable independent and the other dependent. Errors often exist for both measurements. In this work, we examine two regression approaches available to accommodate this situation. They are orthogonal regression and geometric mean regression. Comparisons are made theoretically as well as numerically through an aerosol study examining whether the ratio of organic aerosol to CO would change with age

  17. Standardizing effect size from linear regression models with log-transformed variables for meta-analysis.

    Science.gov (United States)

    Rodríguez-Barranco, Miguel; Tobías, Aurelio; Redondo, Daniel; Molina-Portillo, Elena; Sánchez, María José

    2017-03-17

    Meta-analysis is very useful to summarize the effect of a treatment or a risk factor for a given disease. Often studies report results based on log-transformed variables in order to achieve the principal assumptions of a linear regression model. If this is the case for some, but not all studies, the effects need to be homogenized. We derived a set of formulae to transform absolute changes into relative ones, and vice versa, to allow including all results in a meta-analysis. We applied our procedure to all possible combinations of log-transformed independent or dependent variables. We also evaluated it in a simulation based on two variables either normally or asymmetrically distributed. In all the scenarios, and based on different change criteria, the effect size estimated by the derived set of formulae was equivalent to the real effect size. To avoid biased estimates of the effect, this procedure should be used with caution in the case of independent variables with asymmetric distributions that significantly differ from the normal distribution. We illustrate an application of this procedure by an application to a meta-analysis on the potential effects on neurodevelopment in children exposed to arsenic and manganese. The procedure proposed has been shown to be valid and capable of expressing the effect size of a linear regression model based on different change criteria in the variables. Homogenizing the results from different studies beforehand allows them to be combined in a meta-analysis, independently of whether the transformations had been performed on the dependent and/or independent variables.

  18. HYBRID DATA APPROACH FOR SELECTING EFFECTIVE TEST CASES DURING THE REGRESSION TESTING

    OpenAIRE

    Mohan, M.; Shrimali, Tarun

    2017-01-01

    In the software industry, software testing becomes more important in the entire software development life cycle. Software testing is one of the fundamental components of software quality assurances. Software Testing Life Cycle (STLC)is a process involved in testing the complete software, which includes Regression Testing, Unit Testing, Smoke Testing, Integration Testing, Interface Testing, System Testing & etc. In the STLC of Regression testing, test case selection is one of the most importan...

  19. THE TIME DOMAIN SPECTROSCOPIC SURVEY: VARIABLE SELECTION AND ANTICIPATED RESULTS

    Energy Technology Data Exchange (ETDEWEB)

    Morganson, Eric; Green, Paul J. [Harvard Smithsonian Center for Astrophysics, 60 Garden St, Cambridge, MA 02138 (United States); Anderson, Scott F.; Ruan, John J. [Department of Astronomy, University of Washington, Box 351580, Seattle, WA 98195 (United States); Myers, Adam D. [Department of Physics and Astronomy, University of Wyoming, Laramie, WY 82071 (United States); Eracleous, Michael; Brandt, William Nielsen [Department of Astronomy and Astrophysics, 525 Davey Laboratory, The Pennsylvania State University, University Park, PA 16802 (United States); Kelly, Brandon [Department of Physics, Broida Hall, University of California, Santa Barbara, CA 93106-9530 (United States); Badenes, Carlos [Department of Physics and Astronomy and Pittsburgh Particle Physics, Astrophysics and Cosmology Center (PITT PACC), University of Pittsburgh, 3941 O’Hara St, Pittsburgh, PA 15260 (United States); Bañados, Eduardo [Max-Planck-Institut für Astronomie, Königstuhl 17, D-69117 Heidelberg (Germany); Blanton, Michael R. [Center for Cosmology and Particle Physics, Department of Physics, New York University, 4 Washington Place, New York, NY 10003 (United States); Bershady, Matthew A. [Department of Astronomy, University of Wisconsin, 475 N. Charter St., Madison, WI 53706 (United States); Borissova, Jura [Instituto de Física y Astronomía, Universidad de Valparaíso, Av. Gran Bretaña 1111, Playa Ancha, Casilla 5030, and Millennium Institute of Astrophysics (MAS), Santiago (Chile); Burgett, William S. [GMTO Corp, Suite 300, 251 S. Lake Ave, Pasadena, CA 91101 (United States); Chambers, Kenneth, E-mail: emorganson@cfa.harvard.edu [Institute for Astronomy, University of Hawaii at Manoa, Honolulu, HI 96822 (United States); and others

    2015-06-20

    We present the selection algorithm and anticipated results for the Time Domain Spectroscopic Survey (TDSS). TDSS is an Sloan Digital Sky Survey (SDSS)-IV Extended Baryon Oscillation Spectroscopic Survey (eBOSS) subproject that will provide initial identification spectra of approximately 220,000 luminosity-variable objects (variable stars and active galactic nuclei across 7500 deg{sup 2} selected from a combination of SDSS and multi-epoch Pan-STARRS1 photometry. TDSS will be the largest spectroscopic survey to explicitly target variable objects, avoiding pre-selection on the basis of colors or detailed modeling of specific variability characteristics. Kernel Density Estimate analysis of our target population performed on SDSS Stripe 82 data suggests our target sample will be 95% pure (meaning 95% of objects we select have genuine luminosity variability of a few magnitudes or more). Our final spectroscopic sample will contain roughly 135,000 quasars and 85,000 stellar variables, approximately 4000 of which will be RR Lyrae stars which may be used as outer Milky Way probes. The variability-selected quasar population has a smoother redshift distribution than a color-selected sample, and variability measurements similar to those we develop here may be used to make more uniform quasar samples in large surveys. The stellar variable targets are distributed fairly uniformly across color space, indicating that TDSS will obtain spectra for a wide variety of stellar variables including pulsating variables, stars with significant chromospheric activity, cataclysmic variables, and eclipsing binaries. TDSS will serve as a pathfinder mission to identify and characterize the multitude of variable objects that will be detected photometrically in even larger variability surveys such as Large Synoptic Survey Telescope.

  20. Understanding logistic regression analysis

    OpenAIRE

    Sperandei, Sandro

    2014-01-01

    Logistic regression is used to obtain odds ratio in the presence of more than one explanatory variable. The procedure is quite similar to multiple linear regression, with the exception that the response variable is binomial. The result is the impact of each variable on the odds ratio of the observed event of interest. The main advantage is to avoid confounding effects by analyzing the association of all variables together. In this article, we explain the logistic regression procedure using ex...

  1. PATH ANALYSIS WITH LOGISTIC REGRESSION MODELS : EFFECT ANALYSIS OF FULLY RECURSIVE CAUSAL SYSTEMS OF CATEGORICAL VARIABLES

    OpenAIRE

    Nobuoki, Eshima; Minoru, Tabata; Geng, Zhi; Department of Medical Information Analysis, Faculty of Medicine, Oita Medical University; Department of Applied Mathematics, Faculty of Engineering, Kobe University; Department of Probability and Statistics, Peking University

    2001-01-01

    This paper discusses path analysis of categorical variables with logistic regression models. The total, direct and indirect effects in fully recursive causal systems are considered by using model parameters. These effects can be explained in terms of log odds ratios, uncertainty differences, and an inner product of explanatory variables and a response variable. A study on food choice of alligators as a numerical exampleis reanalysed to illustrate the present approach.

  2. A Simple K-Map Based Variable Selection Scheme in the Direct ...

    African Journals Online (AJOL)

    A multiplexer with (n-l) data select inputs can realise directly a function of n variables. In this paper, a simple k-map based variable selection scheme is proposed such that an n variable logic function can be synthesised using a multiplexer with (n-q) data input variables and q data select variables. The procedure is based on ...

  3. Fasting Glucose and the Risk of Depressive Symptoms: Instrumental-Variable Regression in the Cardiovascular Risk in Young Finns Study.

    Science.gov (United States)

    Wesołowska, Karolina; Elovainio, Marko; Hintsa, Taina; Jokela, Markus; Pulkki-Råback, Laura; Pitkänen, Niina; Lipsanen, Jari; Tukiainen, Janne; Lyytikäinen, Leo-Pekka; Lehtimäki, Terho; Juonala, Markus; Raitakari, Olli; Keltikangas-Järvinen, Liisa

    2017-12-01

    Type 2 diabetes (T2D) has been associated with depressive symptoms, but the causal direction of this association and the underlying mechanisms, such as increased glucose levels, remain unclear. We used instrumental-variable regression with a genetic instrument (Mendelian randomization) to examine a causal role of increased glucose concentrations in the development of depressive symptoms. Data were from the population-based Cardiovascular Risk in Young Finns Study (n = 1217). Depressive symptoms were assessed in 2012 using a modified Beck Depression Inventory (BDI-I). Fasting glucose was measured concurrently with depressive symptoms. A genetic risk score for fasting glucose (with 35 single nucleotide polymorphisms) was used as an instrumental variable for glucose. Glucose was not associated with depressive symptoms in the standard linear regression (B = -0.04, 95% CI [-0.12, 0.04], p = .34), but the instrumental-variable regression showed an inverse association between glucose and depressive symptoms (B = -0.43, 95% CI [-0.79, -0.07], p = .020). The difference between the estimates of standard linear regression and instrumental-variable regression was significant (p = .026) CONCLUSION: Our results suggest that the association between T2D and depressive symptoms is unlikely to be caused by increased glucose concentrations. It seems possible that T2D might be linked to depressive symptoms due to low glucose levels.

  4. Mixed Frequency Data Sampling Regression Models: The R Package midasr

    Directory of Open Access Journals (Sweden)

    Eric Ghysels

    2016-08-01

    Full Text Available When modeling economic relationships it is increasingly common to encounter data sampled at different frequencies. We introduce the R package midasr which enables estimating regression models with variables sampled at different frequencies within a MIDAS regression framework put forward in work by Ghysels, Santa-Clara, and Valkanov (2002. In this article we define a general autoregressive MIDAS regression model with multiple variables of different frequencies and show how it can be specified using the familiar R formula interface and estimated using various optimization methods chosen by the researcher. We discuss how to check the validity of the estimated model both in terms of numerical convergence and statistical adequacy of a chosen regression specification, how to perform model selection based on a information criterion, how to assess forecasting accuracy of the MIDAS regression model and how to obtain a forecast aggregation of different MIDAS regression models. We illustrate the capabilities of the package with a simulated MIDAS regression model and give two empirical examples of application of MIDAS regression.

  5. A novel variable selection approach that iteratively optimizes variable space using weighted binary matrix sampling.

    Science.gov (United States)

    Deng, Bai-chuan; Yun, Yong-huan; Liang, Yi-zeng; Yi, Lun-zhao

    2014-10-07

    In this study, a new optimization algorithm called the Variable Iterative Space Shrinkage Approach (VISSA) that is based on the idea of model population analysis (MPA) is proposed for variable selection. Unlike most of the existing optimization methods for variable selection, VISSA statistically evaluates the performance of variable space in each step of optimization. Weighted binary matrix sampling (WBMS) is proposed to generate sub-models that span the variable subspace. Two rules are highlighted during the optimization procedure. First, the variable space shrinks in each step. Second, the new variable space outperforms the previous one. The second rule, which is rarely satisfied in most of the existing methods, is the core of the VISSA strategy. Compared with some promising variable selection methods such as competitive adaptive reweighted sampling (CARS), Monte Carlo uninformative variable elimination (MCUVE) and iteratively retaining informative variables (IRIV), VISSA showed better prediction ability for the calibration of NIR data. In addition, VISSA is user-friendly; only a few insensitive parameters are needed, and the program terminates automatically without any additional conditions. The Matlab codes for implementing VISSA are freely available on the website: https://sourceforge.net/projects/multivariateanalysis/files/VISSA/.

  6. A numeric comparison of variable selection algorithms for supervised learning

    International Nuclear Information System (INIS)

    Palombo, G.; Narsky, I.

    2009-01-01

    Datasets in modern High Energy Physics (HEP) experiments are often described by dozens or even hundreds of input variables. Reducing a full variable set to a subset that most completely represents information about data is therefore an important task in analysis of HEP data. We compare various variable selection algorithms for supervised learning using several datasets such as, for instance, imaging gamma-ray Cherenkov telescope (MAGIC) data found at the UCI repository. We use classifiers and variable selection methods implemented in the statistical package StatPatternRecognition (SPR), a free open-source C++ package developed in the HEP community ( (http://sourceforge.net/projects/statpatrec/)). For each dataset, we select a powerful classifier and estimate its learning accuracy on variable subsets obtained by various selection algorithms. When possible, we also estimate the CPU time needed for the variable subset selection. The results of this analysis are compared with those published previously for these datasets using other statistical packages such as R and Weka. We show that the most accurate, yet slowest, method is a wrapper algorithm known as generalized sequential forward selection ('Add N Remove R') implemented in SPR.

  7. Quantile Regression Methods

    DEFF Research Database (Denmark)

    Fitzenberger, Bernd; Wilke, Ralf Andreas

    2015-01-01

    if the mean regression model does not. We provide a short informal introduction into the principle of quantile regression which includes an illustrative application from empirical labor market research. This is followed by briefly sketching the underlying statistical model for linear quantile regression based......Quantile regression is emerging as a popular statistical approach, which complements the estimation of conditional mean models. While the latter only focuses on one aspect of the conditional distribution of the dependent variable, the mean, quantile regression provides more detailed insights...... by modeling conditional quantiles. Quantile regression can therefore detect whether the partial effect of a regressor on the conditional quantiles is the same for all quantiles or differs across quantiles. Quantile regression can provide evidence for a statistical relationship between two variables even...

  8. Comparison of climate envelope models developed using expert-selected variables versus statistical selection

    Science.gov (United States)

    Brandt, Laura A.; Benscoter, Allison; Harvey, Rebecca G.; Speroterra, Carolina; Bucklin, David N.; Romañach, Stephanie; Watling, James I.; Mazzotti, Frank J.

    2017-01-01

    Climate envelope models are widely used to describe potential future distribution of species under different climate change scenarios. It is broadly recognized that there are both strengths and limitations to using climate envelope models and that outcomes are sensitive to initial assumptions, inputs, and modeling methods Selection of predictor variables, a central step in modeling, is one of the areas where different techniques can yield varying results. Selection of climate variables to use as predictors is often done using statistical approaches that develop correlations between occurrences and climate data. These approaches have received criticism in that they rely on the statistical properties of the data rather than directly incorporating biological information about species responses to temperature and precipitation. We evaluated and compared models and prediction maps for 15 threatened or endangered species in Florida based on two variable selection techniques: expert opinion and a statistical method. We compared model performance between these two approaches for contemporary predictions, and the spatial correlation, spatial overlap and area predicted for contemporary and future climate predictions. In general, experts identified more variables as being important than the statistical method and there was low overlap in the variable sets (0.9 for area under the curve (AUC) and >0.7 for true skill statistic (TSS). Spatial overlap, which compares the spatial configuration between maps constructed using the different variable selection techniques, was only moderate overall (about 60%), with a great deal of variability across species. Difference in spatial overlap was even greater under future climate projections, indicating additional divergence of model outputs from different variable selection techniques. Our work is in agreement with other studies which have found that for broad-scale species distribution modeling, using statistical methods of variable

  9. Classification and quantitation of milk powder by near-infrared spectroscopy and mutual information-based variable selection and partial least squares

    Science.gov (United States)

    Chen, Hui; Tan, Chao; Lin, Zan; Wu, Tong

    2018-01-01

    Milk is among the most popular nutrient source worldwide, which is of great interest due to its beneficial medicinal properties. The feasibility of the classification of milk powder samples with respect to their brands and the determination of protein concentration is investigated by NIR spectroscopy along with chemometrics. Two datasets were prepared for experiment. One contains 179 samples of four brands for classification and the other contains 30 samples for quantitative analysis. Principal component analysis (PCA) was used for exploratory analysis. Based on an effective model-independent variable selection method, i.e., minimal-redundancy maximal-relevance (MRMR), only 18 variables were selected to construct a partial least-square discriminant analysis (PLS-DA) model. On the test set, the PLS-DA model based on the selected variable set was compared with the full-spectrum PLS-DA model, both of which achieved 100% accuracy. In quantitative analysis, the partial least-square regression (PLSR) model constructed by the selected subset of 260 variables outperforms significantly the full-spectrum model. It seems that the combination of NIR spectroscopy, MRMR and PLS-DA or PLSR is a powerful tool for classifying different brands of milk and determining the protein content.

  10. Adaptive metric kernel regression

    DEFF Research Database (Denmark)

    Goutte, Cyril; Larsen, Jan

    2000-01-01

    Kernel smoothing is a widely used non-parametric pattern recognition technique. By nature, it suffers from the curse of dimensionality and is usually difficult to apply to high input dimensions. In this contribution, we propose an algorithm that adapts the input metric used in multivariate...... regression by minimising a cross-validation estimate of the generalisation error. This allows to automatically adjust the importance of different dimensions. The improvement in terms of modelling performance is illustrated on a variable selection task where the adaptive metric kernel clearly outperforms...

  11. Modeling Source Water TOC Using Hydroclimate Variables and Local Polynomial Regression.

    Science.gov (United States)

    Samson, Carleigh C; Rajagopalan, Balaji; Summers, R Scott

    2016-04-19

    To control disinfection byproduct (DBP) formation in drinking water, an understanding of the source water total organic carbon (TOC) concentration variability can be critical. Previously, TOC concentrations in water treatment plant source waters have been modeled using streamflow data. However, the lack of streamflow data or unimpaired flow scenarios makes it difficult to model TOC. In addition, TOC variability under climate change further exacerbates the problem. Here we proposed a modeling approach based on local polynomial regression that uses climate, e.g. temperature, and land surface, e.g., soil moisture, variables as predictors of TOC concentration, obviating the need for streamflow. The local polynomial approach has the ability to capture non-Gaussian and nonlinear features that might be present in the relationships. The utility of the methodology is demonstrated using source water quality and climate data in three case study locations with surface source waters including river and reservoir sources. The models show good predictive skill in general at these locations, with lower skills at locations with the most anthropogenic influences in their streams. Source water TOC predictive models can provide water treatment utilities important information for making treatment decisions for DBP regulation compliance under future climate scenarios.

  12. Prediction of unwanted pregnancies using logistic regression, probit regression and discriminant analysis.

    Science.gov (United States)

    Ebrahimzadeh, Farzad; Hajizadeh, Ebrahim; Vahabi, Nasim; Almasian, Mohammad; Bakhteyar, Katayoon

    2015-01-01

    Unwanted pregnancy not intended by at least one of the parents has undesirable consequences for the family and the society. In the present study, three classification models were used and compared to predict unwanted pregnancies in an urban population. In this cross-sectional study, 887 pregnant mothers referring to health centers in Khorramabad, Iran, in 2012 were selected by the stratified and cluster sampling; relevant variables were measured and for prediction of unwanted pregnancy, logistic regression, discriminant analysis, and probit regression models and SPSS software version 21 were used. To compare these models, indicators such as sensitivity, specificity, the area under the ROC curve, and the percentage of correct predictions were used. The prevalence of unwanted pregnancies was 25.3%. The logistic and probit regression models indicated that parity and pregnancy spacing, contraceptive methods, household income and number of living male children were related to unwanted pregnancy. The performance of the models based on the area under the ROC curve was 0.735, 0.733, and 0.680 for logistic regression, probit regression, and linear discriminant analysis, respectively. Given the relatively high prevalence of unwanted pregnancies in Khorramabad, it seems necessary to revise family planning programs. Despite the similar accuracy of the models, if the researcher is interested in the interpretability of the results, the use of the logistic regression model is recommended.

  13. A simple approach to power and sample size calculations in logistic regression and Cox regression models.

    Science.gov (United States)

    Vaeth, Michael; Skovlund, Eva

    2004-06-15

    For a given regression problem it is possible to identify a suitably defined equivalent two-sample problem such that the power or sample size obtained for the two-sample problem also applies to the regression problem. For a standard linear regression model the equivalent two-sample problem is easily identified, but for generalized linear models and for Cox regression models the situation is more complicated. An approximately equivalent two-sample problem may, however, also be identified here. In particular, we show that for logistic regression and Cox regression models the equivalent two-sample problem is obtained by selecting two equally sized samples for which the parameters differ by a value equal to the slope times twice the standard deviation of the independent variable and further requiring that the overall expected number of events is unchanged. In a simulation study we examine the validity of this approach to power calculations in logistic regression and Cox regression models. Several different covariate distributions are considered for selected values of the overall response probability and a range of alternatives. For the Cox regression model we consider both constant and non-constant hazard rates. The results show that in general the approach is remarkably accurate even in relatively small samples. Some discrepancies are, however, found in small samples with few events and a highly skewed covariate distribution. Comparison with results based on alternative methods for logistic regression models with a single continuous covariate indicates that the proposed method is at least as good as its competitors. The method is easy to implement and therefore provides a simple way to extend the range of problems that can be covered by the usual formulas for power and sample size determination. Copyright 2004 John Wiley & Sons, Ltd.

  14. Kendall-Theil Robust Line (KTRLine--version 1.0)-A Visual Basic Program for Calculating and Graphing Robust Nonparametric Estimates of Linear-Regression Coefficients Between Two Continuous Variables

    Science.gov (United States)

    Granato, Gregory E.

    2006-01-01

    The Kendall-Theil Robust Line software (KTRLine-version 1.0) is a Visual Basic program that may be used with the Microsoft Windows operating system to calculate parameters for robust, nonparametric estimates of linear-regression coefficients between two continuous variables. The KTRLine software was developed by the U.S. Geological Survey, in cooperation with the Federal Highway Administration, for use in stochastic data modeling with local, regional, and national hydrologic data sets to develop planning-level estimates of potential effects of highway runoff on the quality of receiving waters. The Kendall-Theil robust line was selected because this robust nonparametric method is resistant to the effects of outliers and nonnormality in residuals that commonly characterize hydrologic data sets. The slope of the line is calculated as the median of all possible pairwise slopes between points. The intercept is calculated so that the line will run through the median of input data. A single-line model or a multisegment model may be specified. The program was developed to provide regression equations with an error component for stochastic data generation because nonparametric multisegment regression tools are not available with the software that is commonly used to develop regression models. The Kendall-Theil robust line is a median line and, therefore, may underestimate total mass, volume, or loads unless the error component or a bias correction factor is incorporated into the estimate. Regression statistics such as the median error, the median absolute deviation, the prediction error sum of squares, the root mean square error, the confidence interval for the slope, and the bias correction factor for median estimates are calculated by use of nonparametric methods. These statistics, however, may be used to formulate estimates of mass, volume, or total loads. The program is used to read a two- or three-column tab-delimited input file with variable names in the first row and

  15. A Matlab program for stepwise regression

    Directory of Open Access Journals (Sweden)

    Yanhong Qi

    2016-03-01

    Full Text Available The stepwise linear regression is a multi-variable regression for identifying statistically significant variables in the linear regression equation. In present study, we presented the Matlab program of stepwise regression.

  16. Logic regression and its extensions.

    Science.gov (United States)

    Schwender, Holger; Ruczinski, Ingo

    2010-01-01

    Logic regression is an adaptive classification and regression procedure, initially developed to reveal interacting single nucleotide polymorphisms (SNPs) in genetic association studies. In general, this approach can be used in any setting with binary predictors, when the interaction of these covariates is of primary interest. Logic regression searches for Boolean (logic) combinations of binary variables that best explain the variability in the outcome variable, and thus, reveals variables and interactions that are associated with the response and/or have predictive capabilities. The logic expressions are embedded in a generalized linear regression framework, and thus, logic regression can handle a variety of outcome types, such as binary responses in case-control studies, numeric responses, and time-to-event data. In this chapter, we provide an introduction to the logic regression methodology, list some applications in public health and medicine, and summarize some of the direct extensions and modifications of logic regression that have been proposed in the literature. Copyright © 2010 Elsevier Inc. All rights reserved.

  17. Understanding logistic regression analysis.

    Science.gov (United States)

    Sperandei, Sandro

    2014-01-01

    Logistic regression is used to obtain odds ratio in the presence of more than one explanatory variable. The procedure is quite similar to multiple linear regression, with the exception that the response variable is binomial. The result is the impact of each variable on the odds ratio of the observed event of interest. The main advantage is to avoid confounding effects by analyzing the association of all variables together. In this article, we explain the logistic regression procedure using examples to make it as simple as possible. After definition of the technique, the basic interpretation of the results is highlighted and then some special issues are discussed.

  18. Adaptive Metric Kernel Regression

    DEFF Research Database (Denmark)

    Goutte, Cyril; Larsen, Jan

    1998-01-01

    Kernel smoothing is a widely used nonparametric pattern recognition technique. By nature, it suffers from the curse of dimensionality and is usually difficult to apply to high input dimensions. In this paper, we propose an algorithm that adapts the input metric used in multivariate regression...... by minimising a cross-validation estimate of the generalisation error. This allows one to automatically adjust the importance of different dimensions. The improvement in terms of modelling performance is illustrated on a variable selection task where the adaptive metric kernel clearly outperforms the standard...

  19. Solving the Omitted Variables Problem of Regression Analysis Using the Relative Vertical Position of Observations

    Directory of Open Access Journals (Sweden)

    Jonathan E. Leightner

    2012-01-01

    Full Text Available The omitted variables problem is one of regression analysis’ most serious problems. The standard approach to the omitted variables problem is to find instruments, or proxies, for the omitted variables, but this approach makes strong assumptions that are rarely met in practice. This paper introduces best projection reiterative truncated projected least squares (BP-RTPLS, the third generation of a technique that solves the omitted variables problem without using proxies or instruments. This paper presents a theoretical argument that BP-RTPLS produces unbiased reduced form estimates when there are omitted variables. This paper also provides simulation evidence that shows OLS produces between 250% and 2450% more errors than BP-RTPLS when there are omitted variables and when measurement and round-off error is 1 percent or less. In an example, the government spending multiplier, , is estimated using annual data for the USA between 1929 and 2010.

  20. A simple bias correction in linear regression for quantitative trait association under two-tail extreme selection.

    Science.gov (United States)

    Kwan, Johnny S H; Kung, Annie W C; Sham, Pak C

    2011-09-01

    Selective genotyping can increase power in quantitative trait association. One example of selective genotyping is two-tail extreme selection, but simple linear regression analysis gives a biased genetic effect estimate. Here, we present a simple correction for the bias.

  1. A regression approach for zircaloy-2 in-reactor creep constitutive equations

    International Nuclear Information System (INIS)

    Yung Liu, Y.; Bement, A.L.

    1977-01-01

    In this paper the methodology of multiple regressions as applied to zircaloy-2 in-reactor creep data analysis and construction of constitutive equation are illustrated. While the resulting constitutive equation can be used in creep analysis of in-reactor zircaloy structural components, the methodology itself is entirely general and can be applied to any creep data analysis. From data analysis and model development point of views, both the assumption of independence and prior committment to specific model forms are unacceptable. One would desire means which can not only estimate the required parameters directly from data but also provide basis for model selections, viz., one model against others. Basic understanding of the physics of deformation is important in choosing the forms of starting physical model equations, but the justifications must rely on their abilities in correlating the overall data. The promising aspects of multiple regression creep data analysis are briefly outlined as follows: (1) when there are more than one variable involved, there is no need to make the assumption that each variable affects the response independently. No separate normalizations are required either and the estimation of parameters is obtained by solving many simultaneous equations. The number of simultaneous equations is equal to the number of data sets, (2) regression statistics such as R 2 - and F-statistics provide measures of the significance of regression creep equation in correlating the overall data. The relative weights of each variable on the response can also be obtained. (3) Special regression techniques such as step-wise, ridge, and robust regressions and residual plots, etc., provide diagnostic tools for model selections

  2. Régression orthogonale de trois variables liées Orthogonal Regression of Linked Variables

    Directory of Open Access Journals (Sweden)

    Phelizon J. -F.

    2006-11-01

    Full Text Available On propose dans cet article un algorithme permettant de déterminer les paramètres de l'équation de régression orthogonale de trois variables liées par une relation linéaire. Cet algorithme est remarquablement simple puisqu'il n'implique pas de devoir calculer les valeurs propres de la matrice des covariances. D'autre part, on montre que l'équation obtenue (celle d'une droite dans l'espace à trois dimensions caractérise aussi une droite dans un diagramme triangulaire, ce qui rend l'interprétation des résultats immédiate. L'exposé théorique se poursuit par deux exemples qui ont été effectivement testés sur ordinateur. This article proposes on algorithm for determining the parameters of the equation for the orthogonal regression of three variables linked by a linear relation. This algorithm is remarkably simple in that il does not require the actual values of the covariance matrix to be calculated. In addition, the equation obtained (for a straight line in three-dimensional space is shown to characterize a straight line in a triang ular diagram as well, thus making il immediately possible ta interpret the resulis. The theoretical explanation continues with two examples that were actually tried out on a computer.

  3. An improved partial least-squares regression method for Raman spectroscopy

    Science.gov (United States)

    Momenpour Tehran Monfared, Ali; Anis, Hanan

    2017-10-01

    It is known that the performance of partial least-squares (PLS) regression analysis can be improved using the backward variable selection method (BVSPLS). In this paper, we further improve the BVSPLS based on a novel selection mechanism. The proposed method is based on sorting the weighted regression coefficients, and then the importance of each variable of the sorted list is evaluated using root mean square errors of prediction (RMSEP) criterion in each iteration step. Our Improved BVSPLS (IBVSPLS) method has been applied to leukemia and heparin data sets and led to an improvement in limit of detection of Raman biosensing ranged from 10% to 43% compared to PLS. Our IBVSPLS was also compared to the jack-knifing (simpler) and Genetic Algorithm (more complex) methods. Our method was consistently better than the jack-knifing method and showed either a similar or a better performance compared to the genetic algorithm.

  4. A simple bias correction in linear regression for quantitative trait association under two-tail extreme selection

    OpenAIRE

    Kwan, Johnny S. H.; Kung, Annie W. C.; Sham, Pak C.

    2011-01-01

    Selective genotyping can increase power in quantitative trait association. One example of selective genotyping is two-tail extreme selection, but simple linear regression analysis gives a biased genetic effect estimate. Here, we present a simple correction for the bias. © The Author(s) 2011.

  5. Multiple Regression and Mediator Variables can be used to Avoid Double Counting when Economic Values are Derived using Stochastic Herd Simulation

    DEFF Research Database (Denmark)

    Østergaard, Søren; Ettema, Jehan Frans; Hjortø, Line

    Multiple regression and model building with mediator variables was addressed to avoid double counting when economic values are estimated from data simulated with herd simulation modeling (using the SimHerd model). The simulated incidence of metritis was analyzed statistically as the independent v...... in multiparous cows. The merit of using this approach was demonstrated since the economic value of metritis was estimated to be 81% higher when no mediator variables were included in the multiple regression analysis......Multiple regression and model building with mediator variables was addressed to avoid double counting when economic values are estimated from data simulated with herd simulation modeling (using the SimHerd model). The simulated incidence of metritis was analyzed statistically as the independent...... variable, while using the traits representing the direct effects of metritis on yield, fertility and occurrence of other diseases as mediator variables. The economic value of metritis was estimated to be €78 per 100 cow-years for each 1% increase of metritis in the period of 1-100 days in milk...

  6. Developing a spatial-statistical model and map of historical malaria prevalence in Botswana using a staged variable selection procedure

    Directory of Open Access Journals (Sweden)

    Mabaso Musawenkosi LH

    2007-09-01

    Full Text Available Abstract Background Several malaria risk maps have been developed in recent years, many from the prevalence of infection data collated by the MARA (Mapping Malaria Risk in Africa project, and using various environmental data sets as predictors. Variable selection is a major obstacle due to analytical problems caused by over-fitting, confounding and non-independence in the data. Testing and comparing every combination of explanatory variables in a Bayesian spatial framework remains unfeasible for most researchers. The aim of this study was to develop a malaria risk map using a systematic and practicable variable selection process for spatial analysis and mapping of historical malaria risk in Botswana. Results Of 50 potential explanatory variables from eight environmental data themes, 42 were significantly associated with malaria prevalence in univariate logistic regression and were ranked by the Akaike Information Criterion. Those correlated with higher-ranking relatives of the same environmental theme, were temporarily excluded. The remaining 14 candidates were ranked by selection frequency after running automated step-wise selection procedures on 1000 bootstrap samples drawn from the data. A non-spatial multiple-variable model was developed through step-wise inclusion in order of selection frequency. Previously excluded variables were then re-evaluated for inclusion, using further step-wise bootstrap procedures, resulting in the exclusion of another variable. Finally a Bayesian geo-statistical model using Markov Chain Monte Carlo simulation was fitted to the data, resulting in a final model of three predictor variables, namely summer rainfall, mean annual temperature and altitude. Each was independently and significantly associated with malaria prevalence after allowing for spatial correlation. This model was used to predict malaria prevalence at unobserved locations, producing a smooth risk map for the whole country. Conclusion We have

  7. Auxiliary variables in multiple imputation in regression with missing X: a warning against including too many in small sample research

    Directory of Open Access Journals (Sweden)

    Hardt Jochen

    2012-12-01

    Full Text Available Abstract Background Multiple imputation is becoming increasingly popular. Theoretical considerations as well as simulation studies have shown that the inclusion of auxiliary variables is generally of benefit. Methods A simulation study of a linear regression with a response Y and two predictors X1 and X2 was performed on data with n = 50, 100 and 200 using complete cases or multiple imputation with 0, 10, 20, 40 and 80 auxiliary variables. Mechanisms of missingness were either 100% MCAR or 50% MAR + 50% MCAR. Auxiliary variables had low (r=.10 vs. moderate correlations (r=.50 with X’s and Y. Results The inclusion of auxiliary variables can improve a multiple imputation model. However, inclusion of too many variables leads to downward bias of regression coefficients and decreases precision. When the correlations are low, inclusion of auxiliary variables is not useful. Conclusion More research on auxiliary variables in multiple imputation should be performed. A preliminary rule of thumb could be that the ratio of variables to cases with complete data should not go below 1 : 3.

  8. Machine learning techniques to select variable stars

    Directory of Open Access Journals (Sweden)

    García-Varela Alejandro

    2017-01-01

    Full Text Available In order to perform a supervised classification of variable stars, we propose and evaluate a set of six features extracted from the magnitude density of the light curves. They are used to train automatic classification systems using state-of-the-art classifiers implemented in the R statistical computing environment. We find that random forests is the most successful method to select variables.

  9. No rationale for 1 variable per 10 events criterion for binary logistic regression analysis.

    Science.gov (United States)

    van Smeden, Maarten; de Groot, Joris A H; Moons, Karel G M; Collins, Gary S; Altman, Douglas G; Eijkemans, Marinus J C; Reitsma, Johannes B

    2016-11-24

    Ten events per variable (EPV) is a widely advocated minimal criterion for sample size considerations in logistic regression analysis. Of three previous simulation studies that examined this minimal EPV criterion only one supports the use of a minimum of 10 EPV. In this paper, we examine the reasons for substantial differences between these extensive simulation studies. The current study uses Monte Carlo simulations to evaluate small sample bias, coverage of confidence intervals and mean square error of logit coefficients. Logistic regression models fitted by maximum likelihood and a modified estimation procedure, known as Firth's correction, are compared. The results show that besides EPV, the problems associated with low EPV depend on other factors such as the total sample size. It is also demonstrated that simulation results can be dominated by even a few simulated data sets for which the prediction of the outcome by the covariates is perfect ('separation'). We reveal that different approaches for identifying and handling separation leads to substantially different simulation results. We further show that Firth's correction can be used to improve the accuracy of regression coefficients and alleviate the problems associated with separation. The current evidence supporting EPV rules for binary logistic regression is weak. Given our findings, there is an urgent need for new research to provide guidance for supporting sample size considerations for binary logistic regression analysis.

  10. A brief introduction to regression designs and mixed-effects modelling by a recent convert

    DEFF Research Database (Denmark)

    Balling, Laura Winther

    2008-01-01

    This article discusses the advantages of multiple regression designs over the factorial designs traditionally used in many psycholinguistic experiments. It is shown that regression designs are typically more informative, statistically more powerful and better suited to the analysis of naturalistic...... tasks. The advantages of including both fixed and random effects are demonstrated with reference to linear mixed-effects models, and problems of collinearity, variable distribution and variable selection are discussed. The advantages of these techniques are exemplified in an analysis of a word...

  11. Modelling of binary logistic regression for obesity among secondary students in a rural area of Kedah

    Science.gov (United States)

    Kamaruddin, Ainur Amira; Ali, Zalila; Noor, Norlida Mohd.; Baharum, Adam; Ahmad, Wan Muhamad Amir W.

    2014-07-01

    Logistic regression analysis examines the influence of various factors on a dichotomous outcome by estimating the probability of the event's occurrence. Logistic regression, also called a logit model, is a statistical procedure used to model dichotomous outcomes. In the logit model the log odds of the dichotomous outcome is modeled as a linear combination of the predictor variables. The log odds ratio in logistic regression provides a description of the probabilistic relationship of the variables and the outcome. In conducting logistic regression, selection procedures are used in selecting important predictor variables, diagnostics are used to check that assumptions are valid which include independence of errors, linearity in the logit for continuous variables, absence of multicollinearity, and lack of strongly influential outliers and a test statistic is calculated to determine the aptness of the model. This study used the binary logistic regression model to investigate overweight and obesity among rural secondary school students on the basis of their demographics profile, medical history, diet and lifestyle. The results indicate that overweight and obesity of students are influenced by obesity in family and the interaction between a student's ethnicity and routine meals intake. The odds of a student being overweight and obese are higher for a student having a family history of obesity and for a non-Malay student who frequently takes routine meals as compared to a Malay student.

  12. A Variable-Selection Heuristic for K-Means Clustering.

    Science.gov (United States)

    Brusco, Michael J.; Cradit, J. Dennis

    2001-01-01

    Presents a variable selection heuristic for nonhierarchical (K-means) cluster analysis based on the adjusted Rand index for measuring cluster recovery. Subjected the heuristic to Monte Carlo testing across more than 2,200 datasets. Results indicate that the heuristic is extremely effective at eliminating masking variables. (SLD)

  13. Relationship between rice yield and climate variables in southwest Nigeria using multiple linear regression and support vector machine analysis

    Science.gov (United States)

    Oguntunde, Philip G.; Lischeid, Gunnar; Dietrich, Ottfried

    2018-03-01

    This study examines the variations of climate variables and rice yield and quantifies the relationships among them using multiple linear regression, principal component analysis, and support vector machine (SVM) analysis in southwest Nigeria. The climate and yield data used was for a period of 36 years between 1980 and 2015. Similar to the observed decrease ( P 1 and explained 83.1% of the total variance of predictor variables. The SVM regression function using the scores of the first principal component explained about 75% of the variance in rice yield data and linear regression about 64%. SVM regression between annual solar radiation values and yield explained 67% of the variance. Only the first component of the principal component analysis (PCA) exhibited a clear long-term trend and sometimes short-term variance similar to that of rice yield. Short-term fluctuations of the scores of the PC1 are closely coupled to those of rice yield during the 1986-1993 and the 2006-2013 periods thereby revealing the inter-annual sensitivity of rice production to climate variability. Solar radiation stands out as the climate variable of highest influence on rice yield, and the influence was especially strong during monsoon and post-monsoon periods, which correspond to the vegetative, booting, flowering, and grain filling stages in the study area. The outcome is expected to provide more in-depth regional-specific climate-rice linkage for screening of better cultivars that can positively respond to future climate fluctuations as well as providing information that may help optimized planting dates for improved radiation use efficiency in the study area.

  14. A Permutation Approach for Selecting the Penalty Parameter in Penalized Model Selection

    Science.gov (United States)

    Sabourin, Jeremy A; Valdar, William; Nobel, Andrew B

    2015-01-01

    Summary We describe a simple, computationally effcient, permutation-based procedure for selecting the penalty parameter in LASSO penalized regression. The procedure, permutation selection, is intended for applications where variable selection is the primary focus, and can be applied in a variety of structural settings, including that of generalized linear models. We briefly discuss connections between permutation selection and existing theory for the LASSO. In addition, we present a simulation study and an analysis of real biomedical data sets in which permutation selection is compared with selection based on the following: cross-validation (CV), the Bayesian information criterion (BIC), Scaled Sparse Linear Regression, and a selection method based on recently developed testing procedures for the LASSO. PMID:26243050

  15. Predictive market segmentation model: An application of logistic regression model and CHAID procedure

    Directory of Open Access Journals (Sweden)

    Soldić-Aleksić Jasna

    2009-01-01

    Full Text Available Market segmentation presents one of the key concepts of the modern marketing. The main goal of market segmentation is focused on creating groups (segments of customers that have similar characteristics, needs, wishes and/or similar behavior regarding the purchase of concrete product/service. Companies can create specific marketing plan for each of these segments and therefore gain short or long term competitive advantage on the market. Depending on the concrete marketing goal, different segmentation schemes and techniques may be applied. This paper presents a predictive market segmentation model based on the application of logistic regression model and CHAID analysis. The logistic regression model was used for the purpose of variables selection (from the initial pool of eleven variables which are statistically significant for explaining the dependent variable. Selected variables were afterwards included in the CHAID procedure that generated the predictive market segmentation model. The model results are presented on the concrete empirical example in the following form: summary model results, CHAID tree, Gain chart, Index chart, risk and classification tables.

  16. Bayesian nonparametric variable selection as an exploratory tool for discovering differentially expressed genes.

    Science.gov (United States)

    Shahbaba, Babak; Johnson, Wesley O

    2013-05-30

    High-throughput scientific studies involving no clear a priori hypothesis are common. For example, a large-scale genomic study of a disease may examine thousands of genes without hypothesizing that any specific gene is responsible for the disease. In these studies, the objective is to explore a large number of possible factors (e.g., genes) in order to identify a small number that will be considered in follow-up studies that tend to be more thorough and on smaller scales. A simple, hierarchical, linear regression model with random coefficients is assumed for case-control data that correspond to each gene. The specific model used will be seen to be related to a standard Bayesian variable selection model. Relatively large regression coefficients correspond to potential differences in responses for cases versus controls and thus to genes that might 'matter'. For large-scale studies, and using a Dirichlet process mixture model for the regression coefficients, we are able to find clusters of regression effects of genes with increasing potential effect or 'relevance', in relation to the outcome of interest. One cluster will always correspond to genes whose coefficients are in a neighborhood that is relatively close to zero and will be deemed least relevant. Other clusters will correspond to increasing magnitudes of the random/latent regression coefficients. Using simulated data, we demonstrate that our approach could be quite effective in finding relevant genes compared with several alternative methods. We apply our model to two large-scale studies. The first study involves transcriptome analysis of infection by human cytomegalovirus. The second study's objective is to identify differentially expressed genes between two types of leukemia. Copyright © 2012 John Wiley & Sons, Ltd.

  17. Bias correction by use of errors-in-variables regression models in studies with K-X-ray fluorescence bone lead measurements.

    Science.gov (United States)

    Lamadrid-Figueroa, Héctor; Téllez-Rojo, Martha M; Angeles, Gustavo; Hernández-Ávila, Mauricio; Hu, Howard

    2011-01-01

    In-vivo measurement of bone lead by means of K-X-ray fluorescence (KXRF) is the preferred biological marker of chronic exposure to lead. Unfortunately, considerable measurement error associated with KXRF estimations can introduce bias in estimates of the effect of bone lead when this variable is included as the exposure in a regression model. Estimates of uncertainty reported by the KXRF instrument reflect the variance of the measurement error and, although they can be used to correct the measurement error bias, they are seldom used in epidemiological statistical analyzes. Errors-in-variables regression (EIV) allows for correction of bias caused by measurement error in predictor variables, based on the knowledge of the reliability of such variables. The authors propose a way to obtain reliability coefficients for bone lead measurements from uncertainty data reported by the KXRF instrument and compare, by the use of Monte Carlo simulations, results obtained using EIV regression models vs. those obtained by the standard procedures. Results of the simulations show that Ordinary Least Square (OLS) regression models provide severely biased estimates of effect, and that EIV provides nearly unbiased estimates. Although EIV effect estimates are more imprecise, their mean squared error is much smaller than that of OLS estimates. In conclusion, EIV is a better alternative than OLS to estimate the effect of bone lead when measured by KXRF. Copyright © 2010 Elsevier Inc. All rights reserved.

  18. Regression model development and computational procedures to support estimation of real-time concentrations and loads of selected constituents in two tributaries to Lake Houston near Houston, Texas, 2005-9

    Science.gov (United States)

    Lee, Michael T.; Asquith, William H.; Oden, Timothy D.

    2012-01-01

    In December 2005, the U.S. Geological Survey (USGS), in cooperation with the City of Houston, Texas, began collecting discrete water-quality samples for nutrients, total organic carbon, bacteria (Escherichia coli and total coliform), atrazine, and suspended sediment at two USGS streamflow-gaging stations that represent watersheds contributing to Lake Houston (08068500 Spring Creek near Spring, Tex., and 08070200 East Fork San Jacinto River near New Caney, Tex.). Data from the discrete water-quality samples collected during 2005–9, in conjunction with continuously monitored real-time data that included streamflow and other physical water-quality properties (specific conductance, pH, water temperature, turbidity, and dissolved oxygen), were used to develop regression models for the estimation of concentrations of water-quality constituents of substantial source watersheds to Lake Houston. The potential explanatory variables included discharge (streamflow), specific conductance, pH, water temperature, turbidity, dissolved oxygen, and time (to account for seasonal variations inherent in some water-quality data). The response variables (the selected constituents) at each site were nitrite plus nitrate nitrogen, total phosphorus, total organic carbon, E. coli, atrazine, and suspended sediment. The explanatory variables provide easily measured quantities to serve as potential surrogate variables to estimate concentrations of the selected constituents through statistical regression. Statistical regression also facilitates accompanying estimates of uncertainty in the form of prediction intervals. Each regression model potentially can be used to estimate concentrations of a given constituent in real time. Among other regression diagnostics, the diagnostics used as indicators of general model reliability and reported herein include the adjusted R-squared, the residual standard error, residual plots, and p-values. Adjusted R-squared values for the Spring Creek models ranged

  19. ENSEMBLE VARIABILITY OF NEAR-INFRARED-SELECTED ACTIVE GALACTIC NUCLEI

    International Nuclear Information System (INIS)

    Kouzuma, S.; Yamaoka, H.

    2012-01-01

    We present the properties of the ensemble variability V for nearly 5000 near-infrared active galactic nuclei (AGNs) selected from the catalog of Quasars and Active Galactic Nuclei (13th Edition) and the SDSS-DR7 quasar catalog. From three near-infrared point source catalogs, namely, Two Micron All Sky Survey (2MASS), Deep Near Infrared Survey (DENIS), and UKIDSS/LAS catalogs, we extract 2MASS-DENIS and 2MASS-UKIDSS counterparts for cataloged AGNs by cross-identification between catalogs. We further select variable AGNs based on an optimal criterion for selecting the variable sources. The sample objects are divided into subsets according to whether near-infrared light originates by optical emission or by near-infrared emission in the rest frame; and we examine the correlations of the ensemble variability with the rest-frame wavelength, redshift, luminosity, and rest-frame time lag. In addition, we also examine the correlations of variability amplitude with optical variability, radio intensity, and radio-to-optical flux ratio. The rest-frame optical variability of our samples shows negative correlations with luminosity and positive correlations with rest-frame time lag (i.e., the structure function, SF), and this result is consistent with previous analyses. However, no well-known negative correlation exists between the rest-frame wavelength and optical variability. This inconsistency might be due to a biased sampling of high-redshift AGNs. Near-infrared variability in the rest frame is anticorrelated with the rest-frame wavelength, which is consistent with previous suggestions. However, correlations of near-infrared variability with luminosity and rest-frame time lag are the opposite of these correlations of the optical variability; that is, the near-infrared variability is positively correlated with luminosity but negatively correlated with the rest-frame time lag. Because these trends are qualitatively consistent with the properties of radio-loud quasars reported

  20. No rationale for 1 variable per 10 events criterion for binary logistic regression analysis

    Directory of Open Access Journals (Sweden)

    Maarten van Smeden

    2016-11-01

    Full Text Available Abstract Background Ten events per variable (EPV is a widely advocated minimal criterion for sample size considerations in logistic regression analysis. Of three previous simulation studies that examined this minimal EPV criterion only one supports the use of a minimum of 10 EPV. In this paper, we examine the reasons for substantial differences between these extensive simulation studies. Methods The current study uses Monte Carlo simulations to evaluate small sample bias, coverage of confidence intervals and mean square error of logit coefficients. Logistic regression models fitted by maximum likelihood and a modified estimation procedure, known as Firth’s correction, are compared. Results The results show that besides EPV, the problems associated with low EPV depend on other factors such as the total sample size. It is also demonstrated that simulation results can be dominated by even a few simulated data sets for which the prediction of the outcome by the covariates is perfect (‘separation’. We reveal that different approaches for identifying and handling separation leads to substantially different simulation results. We further show that Firth’s correction can be used to improve the accuracy of regression coefficients and alleviate the problems associated with separation. Conclusions The current evidence supporting EPV rules for binary logistic regression is weak. Given our findings, there is an urgent need for new research to provide guidance for supporting sample size considerations for binary logistic regression analysis.

  1. Significance testing in ridge regression for genetic data

    Directory of Open Access Journals (Sweden)

    De Iorio Maria

    2011-09-01

    Full Text Available Abstract Background Technological developments have increased the feasibility of large scale genetic association studies. Densely typed genetic markers are obtained using SNP arrays, next-generation sequencing technologies and imputation. However, SNPs typed using these methods can be highly correlated due to linkage disequilibrium among them, and standard multiple regression techniques fail with these data sets due to their high dimensionality and correlation structure. There has been increasing interest in using penalised regression in the analysis of high dimensional data. Ridge regression is one such penalised regression technique which does not perform variable selection, instead estimating a regression coefficient for each predictor variable. It is therefore desirable to obtain an estimate of the significance of each ridge regression coefficient. Results We develop and evaluate a test of significance for ridge regression coefficients. Using simulation studies, we demonstrate that the performance of the test is comparable to that of a permutation test, with the advantage of a much-reduced computational cost. We introduce the p-value trace, a plot of the negative logarithm of the p-values of ridge regression coefficients with increasing shrinkage parameter, which enables the visualisation of the change in p-value of the regression coefficients with increasing penalisation. We apply the proposed method to a lung cancer case-control data set from EPIC, the European Prospective Investigation into Cancer and Nutrition. Conclusions The proposed test is a useful alternative to a permutation test for the estimation of the significance of ridge regression coefficients, at a much-reduced computational cost. The p-value trace is an informative graphical tool for evaluating the results of a test of significance of ridge regression coefficients as the shrinkage parameter increases, and the proposed test makes its production computationally feasible.

  2. [From clinical judgment to linear regression model.

    Science.gov (United States)

    Palacios-Cruz, Lino; Pérez, Marcela; Rivas-Ruiz, Rodolfo; Talavera, Juan O

    2013-01-01

    When we think about mathematical models, such as linear regression model, we think that these terms are only used by those engaged in research, a notion that is far from the truth. Legendre described the first mathematical model in 1805, and Galton introduced the formal term in 1886. Linear regression is one of the most commonly used regression models in clinical practice. It is useful to predict or show the relationship between two or more variables as long as the dependent variable is quantitative and has normal distribution. Stated in another way, the regression is used to predict a measure based on the knowledge of at least one other variable. Linear regression has as it's first objective to determine the slope or inclination of the regression line: Y = a + bx, where "a" is the intercept or regression constant and it is equivalent to "Y" value when "X" equals 0 and "b" (also called slope) indicates the increase or decrease that occurs when the variable "x" increases or decreases in one unit. In the regression line, "b" is called regression coefficient. The coefficient of determination (R 2 ) indicates the importance of independent variables in the outcome.

  3. Relationship between rice yield and climate variables in southwest Nigeria using multiple linear regression and support vector machine analysis.

    Science.gov (United States)

    Oguntunde, Philip G; Lischeid, Gunnar; Dietrich, Ottfried

    2018-03-01

    This study examines the variations of climate variables and rice yield and quantifies the relationships among them using multiple linear regression, principal component analysis, and support vector machine (SVM) analysis in southwest Nigeria. The climate and yield data used was for a period of 36 years between 1980 and 2015. Similar to the observed decrease (P  1 and explained 83.1% of the total variance of predictor variables. The SVM regression function using the scores of the first principal component explained about 75% of the variance in rice yield data and linear regression about 64%. SVM regression between annual solar radiation values and yield explained 67% of the variance. Only the first component of the principal component analysis (PCA) exhibited a clear long-term trend and sometimes short-term variance similar to that of rice yield. Short-term fluctuations of the scores of the PC1 are closely coupled to those of rice yield during the 1986-1993 and the 2006-2013 periods thereby revealing the inter-annual sensitivity of rice production to climate variability. Solar radiation stands out as the climate variable of highest influence on rice yield, and the influence was especially strong during monsoon and post-monsoon periods, which correspond to the vegetative, booting, flowering, and grain filling stages in the study area. The outcome is expected to provide more in-depth regional-specific climate-rice linkage for screening of better cultivars that can positively respond to future climate fluctuations as well as providing information that may help optimized planting dates for improved radiation use efficiency in the study area.

  4. Modeling soil organic matter (SOM) from satellite data using VISNIR-SWIR spectroscopy and PLS regression with step-down variable selection algorithm: case study of Campos Amazonicos National Park savanna enclave, Brazil

    Science.gov (United States)

    Rosero-Vlasova, O.; Borini Alves, D.; Vlassova, L.; Perez-Cabello, F.; Montorio Lloveria, R.

    2017-10-01

    Deforestation in Amazon basin due, among other factors, to frequent wildfires demands continuous post-fire monitoring of soil and vegetation. Thus, the study posed two objectives: (1) evaluate the capacity of Visible - Near InfraRed - ShortWave InfraRed (VIS-NIR-SWIR) spectroscopy to estimate soil organic matter (SOM) in fire-affected soils, and (2) assess the feasibility of SOM mapping from satellite images. For this purpose, 30 soil samples (surface layer) were collected in 2016 in areas of grass and riparian vegetation of Campos Amazonicos National Park, Brazil, repeatedly affected by wildfires. Standard laboratory procedures were applied to determine SOM. Reflectance spectra of soils were obtained in controlled laboratory conditions using Fieldspec4 spectroradiometer (spectral range 350nm- 2500nm). Measured spectra were resampled to simulate reflectances for Landsat-8, Sentinel-2 and EnMap spectral bands, used as predictors in SOM models developed using Partial Least Squares regression and step-down variable selection algorithm (PLSR-SD). The best fit was achieved with models based on reflectances simulated for EnMap bands (R2=0.93; R2cv=0.82 and NMSE=0.07; NMSEcv=0.19). The model uses only 8 out of 244 predictors (bands) chosen by the step-down variable selection algorithm. The least reliable estimates (R2=0.55 and R2cv=0.40 and NMSE=0.43; NMSEcv=0.60) resulted from Landsat model, while Sentinel-2 model showed R2=0.68 and R2cv=0.63; NMSE=0.31 and NMSEcv=0.38. The results confirm high potential of VIS-NIR-SWIR spectroscopy for SOM estimation. Application of step-down produces sparser and better-fit models. Finally, SOM can be estimated with an acceptable accuracy (NMSE 0.35) from EnMap and Sentinel-2 data enabling mapping and analysis of impacts of repeated wildfires on soils in the study area.

  5. Landslide Hazard Mapping in Rwanda Using Logistic Regression

    Science.gov (United States)

    Piller, A.; Anderson, E.; Ballard, H.

    2015-12-01

    Landslides in the United States cause more than $1 billion in damages and 50 deaths per year (USGS 2014). Globally, figures are much more grave, yet monitoring, mapping and forecasting of these hazards are less than adequate. Seventy-five percent of the population of Rwanda earns a living from farming, mostly subsistence. Loss of farmland, housing, or life, to landslides is a very real hazard. Landslides in Rwanda have an impact at the economic, social, and environmental level. In a developing nation that faces challenges in tracking, cataloging, and predicting the numerous landslides that occur each year, satellite imagery and spatial analysis allow for remote study. We have focused on the development of a landslide inventory and a statistical methodology for assessing landslide hazards. Using logistic regression on approximately 30 test variables (i.e. slope, soil type, land cover, etc.) and a sample of over 200 landslides, we determine which variables are statistically most relevant to landslide occurrence in Rwanda. A preliminary predictive hazard map for Rwanda has been produced, using the variables selected from the logistic regression analysis.

  6. Regression dilution bias: tools for correction methods and sample size calculation.

    Science.gov (United States)

    Berglund, Lars

    2012-08-01

    Random errors in measurement of a risk factor will introduce downward bias of an estimated association to a disease or a disease marker. This phenomenon is called regression dilution bias. A bias correction may be made with data from a validity study or a reliability study. In this article we give a non-technical description of designs of reliability studies with emphasis on selection of individuals for a repeated measurement, assumptions of measurement error models, and correction methods for the slope in a simple linear regression model where the dependent variable is a continuous variable. Also, we describe situations where correction for regression dilution bias is not appropriate. The methods are illustrated with the association between insulin sensitivity measured with the euglycaemic insulin clamp technique and fasting insulin, where measurement of the latter variable carries noticeable random error. We provide software tools for estimation of a corrected slope in a simple linear regression model assuming data for a continuous dependent variable and a continuous risk factor from a main study and an additional measurement of the risk factor in a reliability study. Also, we supply programs for estimation of the number of individuals needed in the reliability study and for choice of its design. Our conclusion is that correction for regression dilution bias is seldom applied in epidemiological studies. This may cause important effects of risk factors with large measurement errors to be neglected.

  7. A flow system for generation of concentration perturbation in two-dimensional correlation near-infrared spectroscopy: application to variable selection in multivariate calibration.

    Science.gov (United States)

    Pereira, Claudete Fernandes; Pasquini, Celio

    2010-05-01

    A flow system is proposed to produce a concentration perturbation in liquid samples, aiming at the generation of two-dimensional correlation near-infrared spectra. The system presents advantages in relation to batch systems employed for the same purpose: the experiments are accomplished in a closed system; application of perturbation is rapid and easy; and the experiments can be carried out with micro-scale volumes. The perturbation system has been evaluated in the investigation and selection of relevant variables for multivariate calibration models for the determination of quality parameters of gasoline, including ethanol content, MON (motor octane number), and RON (research octane number). The main advantage of this variable selection approach is the direct association between spectral features and chemical composition, allowing easy interpretation of the regression models.

  8. Latent Variable Regression 4-Level Hierarchical Model Using Multisite Multiple-Cohorts Longitudinal Data. CRESST Report 801

    Science.gov (United States)

    Choi, Kilchan

    2011-01-01

    This report explores a new latent variable regression 4-level hierarchical model for monitoring school performance over time using multisite multiple-cohorts longitudinal data. This kind of data set has a 4-level hierarchical structure: time-series observation nested within students who are nested within different cohorts of students. These…

  9. The cross-validated AUC for MCP-logistic regression with high-dimensional data.

    Science.gov (United States)

    Jiang, Dingfeng; Huang, Jian; Zhang, Ying

    2013-10-01

    We propose a cross-validated area under the receiving operator characteristic (ROC) curve (CV-AUC) criterion for tuning parameter selection for penalized methods in sparse, high-dimensional logistic regression models. We use this criterion in combination with the minimax concave penalty (MCP) method for variable selection. The CV-AUC criterion is specifically designed for optimizing the classification performance for binary outcome data. To implement the proposed approach, we derive an efficient coordinate descent algorithm to compute the MCP-logistic regression solution surface. Simulation studies are conducted to evaluate the finite sample performance of the proposed method and its comparison with the existing methods including the Akaike information criterion (AIC), Bayesian information criterion (BIC) or Extended BIC (EBIC). The model selected based on the CV-AUC criterion tends to have a larger predictive AUC and smaller classification error than those with tuning parameters selected using the AIC, BIC or EBIC. We illustrate the application of the MCP-logistic regression with the CV-AUC criterion on three microarray datasets from the studies that attempt to identify genes related to cancers. Our simulation studies and data examples demonstrate that the CV-AUC is an attractive method for tuning parameter selection for penalized methods in high-dimensional logistic regression models.

  10. Petroleomics by electrospray ionization FT-ICR mass spectrometry coupled to partial least squares with variable selection methods: prediction of the total acid number of crude oils.

    Science.gov (United States)

    Terra, Luciana A; Filgueiras, Paulo R; Tose, Lílian V; Romão, Wanderson; de Souza, Douglas D; de Castro, Eustáquio V R; de Oliveira, Mirela S L; Dias, Júlio C M; Poppi, Ronei J

    2014-10-07

    Negative-ion mode electrospray ionization, ESI(-), with Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS) was coupled to a Partial Least Squares (PLS) regression and variable selection methods to estimate the total acid number (TAN) of Brazilian crude oil samples. Generally, ESI(-)-FT-ICR mass spectra present a power of resolution of ca. 500,000 and a mass accuracy less than 1 ppm, producing a data matrix containing over 5700 variables per sample. These variables correspond to heteroatom-containing species detected as deprotonated molecules, [M - H](-) ions, which are identified primarily as naphthenic acids, phenols and carbazole analog species. The TAN values for all samples ranged from 0.06 to 3.61 mg of KOH g(-1). To facilitate the spectral interpretation, three methods of variable selection were studied: variable importance in the projection (VIP), interval partial least squares (iPLS) and elimination of uninformative variables (UVE). The UVE method seems to be more appropriate for selecting important variables, reducing the dimension of the variables to 183 and producing a root mean square error of prediction of 0.32 mg of KOH g(-1). By reducing the size of the data, it was possible to relate the selected variables with their corresponding molecular formulas, thus identifying the main chemical species responsible for the TAN values.

  11. Variable Selection for Nonparametric Gaussian Process Priors: Models and Computational Strategies.

    Science.gov (United States)

    Savitsky, Terrance; Vannucci, Marina; Sha, Naijun

    2011-02-01

    This paper presents a unified treatment of Gaussian process models that extends to data from the exponential dispersion family and to survival data. Our specific interest is in the analysis of data sets with predictors that have an a priori unknown form of possibly nonlinear associations to the response. The modeling approach we describe incorporates Gaussian processes in a generalized linear model framework to obtain a class of nonparametric regression models where the covariance matrix depends on the predictors. We consider, in particular, continuous, categorical and count responses. We also look into models that account for survival outcomes. We explore alternative covariance formulations for the Gaussian process prior and demonstrate the flexibility of the construction. Next, we focus on the important problem of selecting variables from the set of possible predictors and describe a general framework that employs mixture priors. We compare alternative MCMC strategies for posterior inference and achieve a computationally efficient and practical approach. We demonstrate performances on simulated and benchmark data sets.

  12. Regression Models For Multivariate Count Data.

    Science.gov (United States)

    Zhang, Yiwen; Zhou, Hua; Zhou, Jin; Sun, Wei

    2017-01-01

    Data with multivariate count responses frequently occur in modern applications. The commonly used multinomial-logit model is limiting due to its restrictive mean-variance structure. For instance, analyzing count data from the recent RNA-seq technology by the multinomial-logit model leads to serious errors in hypothesis testing. The ubiquity of over-dispersion and complicated correlation structures among multivariate counts calls for more flexible regression models. In this article, we study some generalized linear models that incorporate various correlation structures among the counts. Current literature lacks a treatment of these models, partly due to the fact that they do not belong to the natural exponential family. We study the estimation, testing, and variable selection for these models in a unifying framework. The regression models are compared on both synthetic and real RNA-seq data.

  13. Characterizing the Optical Variability of Bright Blazars: Variability-based Selection of Fermi Active Galactic Nuclei

    Science.gov (United States)

    Ruan, John J.; Anderson, Scott F.; MacLeod, Chelsea L.; Becker, Andrew C.; Burnett, T. H.; Davenport, James R. A.; Ivezić, Željko; Kochanek, Christopher S.; Plotkin, Richard M.; Sesar, Branimir; Stuart, J. Scott

    2012-11-01

    We investigate the use of optical photometric variability to select and identify blazars in large-scale time-domain surveys, in part to aid in the identification of blazar counterparts to the ~30% of γ-ray sources in the Fermi 2FGL catalog still lacking reliable associations. Using data from the optical LINEAR asteroid survey, we characterize the optical variability of blazars by fitting a damped random walk model to individual light curves with two main model parameters, the characteristic timescales of variability τ, and driving amplitudes on short timescales \\hat{\\sigma }. Imposing cuts on minimum τ and \\hat{\\sigma } allows for blazar selection with high efficiency E and completeness C. To test the efficacy of this approach, we apply this method to optically variable LINEAR objects that fall within the several-arcminute error ellipses of γ-ray sources in the Fermi 2FGL catalog. Despite the extreme stellar contamination at the shallow depth of the LINEAR survey, we are able to recover previously associated optical counterparts to Fermi active galactic nuclei with E >= 88% and C = 88% in Fermi 95% confidence error ellipses having semimajor axis r beaming. After correcting for beaming, we estimate that the characteristic timescale of blazar variability is ~3 years in the rest frame of the jet, in contrast with the ~320 day disk flux timescale observed in quasars. The variability-based selection method presented will be useful for blazar identification in time-domain optical surveys and is also a probe of jet physics.

  14. Predictive and Descriptive CoMFA Models: The Effect of Variable Selection.

    Science.gov (United States)

    Sepehri, Bakhtyar; Omidikia, Nematollah; Kompany-Zareh, Mohsen; Ghavami, Raouf

    2018-01-01

    Aims & Scope: In this research, 8 variable selection approaches were used to investigate the effect of variable selection on the predictive power and stability of CoMFA models. Three data sets including 36 EPAC antagonists, 79 CD38 inhibitors and 57 ATAD2 bromodomain inhibitors were modelled by CoMFA. First of all, for all three data sets, CoMFA models with all CoMFA descriptors were created then by applying each variable selection method a new CoMFA model was developed so for each data set, 9 CoMFA models were built. Obtained results show noisy and uninformative variables affect CoMFA results. Based on created models, applying 5 variable selection approaches including FFD, SRD-FFD, IVE-PLS, SRD-UVEPLS and SPA-jackknife increases the predictive power and stability of CoMFA models significantly. Among them, SPA-jackknife removes most of the variables while FFD retains most of them. FFD and IVE-PLS are time consuming process while SRD-FFD and SRD-UVE-PLS run need to few seconds. Also applying FFD, SRD-FFD, IVE-PLS, SRD-UVE-PLS protect CoMFA countor maps information for both fields. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

  15. THE REGRESSION MODEL OF IRAN LIBRARIES ORGANIZATIONAL CLIMATE.

    Science.gov (United States)

    Jahani, Mohammad Ali; Yaminfirooz, Mousa; Siamian, Hasan

    2015-10-01

    The purpose of this study was to drawing a regression model of organizational climate of central libraries of Iran's universities. This study is an applied research. The statistical population of this study consisted of 96 employees of the central libraries of Iran's public universities selected among the 117 universities affiliated to the Ministry of Health by Stratified Sampling method (510 people). Climate Qual localized questionnaire was used as research tools. For predicting the organizational climate pattern of the libraries is used from the multivariate linear regression and track diagram. of the 9 variables affecting organizational climate, 5 variables of innovation, teamwork, customer service, psychological safety and deep diversity play a major role in prediction of the organizational climate of Iran's libraries. The results also indicate that each of these variables with different coefficient have the power to predict organizational climate but the climate score of psychological safety (0.94) plays a very crucial role in predicting the organizational climate. Track diagram showed that five variables of teamwork, customer service, psychological safety, deep diversity and innovation directly effects on the organizational climate variable that contribution of the team work from this influence is more than any other variables. Of the indicator of the organizational climate of climateQual, the contribution of the team work from this influence is more than any other variables that reinforcement of teamwork in academic libraries can be more effective in improving the organizational climate of this type libraries.

  16. The Properties of Model Selection when Retaining Theory Variables

    DEFF Research Database (Denmark)

    Hendry, David F.; Johansen, Søren

    Economic theories are often fitted directly to data to avoid possible model selection biases. We show that embedding a theory model that specifies the correct set of m relevant exogenous variables, x{t}, within the larger set of m+k candidate variables, (x{t},w{t}), then selection over the second...... set by their statistical significance can be undertaken without affecting the estimator distribution of the theory parameters. This strategy returns the theory-parameter estimates when the theory is correct, yet protects against the theory being under-specified because some w{t} are relevant....

  17. Stock price forecasting for companies listed on Tehran stock exchange using multivariate adaptive regression splines model and semi-parametric splines technique

    Science.gov (United States)

    Rounaghi, Mohammad Mahdi; Abbaszadeh, Mohammad Reza; Arashi, Mohammad

    2015-11-01

    One of the most important topics of interest to investors is stock price changes. Investors whose goals are long term are sensitive to stock price and its changes and react to them. In this regard, we used multivariate adaptive regression splines (MARS) model and semi-parametric splines technique for predicting stock price in this study. The MARS model as a nonparametric method is an adaptive method for regression and it fits for problems with high dimensions and several variables. semi-parametric splines technique was used in this study. Smoothing splines is a nonparametric regression method. In this study, we used 40 variables (30 accounting variables and 10 economic variables) for predicting stock price using the MARS model and using semi-parametric splines technique. After investigating the models, we select 4 accounting variables (book value per share, predicted earnings per share, P/E ratio and risk) as influencing variables on predicting stock price using the MARS model. After fitting the semi-parametric splines technique, only 4 accounting variables (dividends, net EPS, EPS Forecast and P/E Ratio) were selected as variables effective in forecasting stock prices.

  18. Regression: The Apple Does Not Fall Far From the Tree.

    Science.gov (United States)

    Vetter, Thomas R; Schober, Patrick

    2018-05-15

    Researchers and clinicians are frequently interested in either: (1) assessing whether there is a relationship or association between 2 or more variables and quantifying this association; or (2) determining whether 1 or more variables can predict another variable. The strength of such an association is mainly described by the correlation. However, regression analysis and regression models can be used not only to identify whether there is a significant relationship or association between variables but also to generate estimations of such a predictive relationship between variables. This basic statistical tutorial discusses the fundamental concepts and techniques related to the most common types of regression analysis and modeling, including simple linear regression, multiple regression, logistic regression, ordinal regression, and Poisson regression, as well as the common yet often underrecognized phenomenon of regression toward the mean. The various types of regression analysis are powerful statistical techniques, which when appropriately applied, can allow for the valid interpretation of complex, multifactorial data. Regression analysis and models can assess whether there is a relationship or association between 2 or more observed variables and estimate the strength of this association, as well as determine whether 1 or more variables can predict another variable. Regression is thus being applied more commonly in anesthesia, perioperative, critical care, and pain research. However, it is crucial to note that regression can identify plausible risk factors; it does not prove causation (a definitive cause and effect relationship). The results of a regression analysis instead identify independent (predictor) variable(s) associated with the dependent (outcome) variable. As with other statistical methods, applying regression requires that certain assumptions be met, which can be tested with specific diagnostics.

  19. Diagnosis of cranial hemangioma: Comparison between logistic regression analysis and neuronal network

    International Nuclear Information System (INIS)

    Arana, E.; Marti-Bonmati, L.; Bautista, D.; Paredes, R.

    1998-01-01

    To study the utility of logistic regression and the neuronal network in the diagnosis of cranial hemangiomas. Fifteen patients presenting hemangiomas were selected form a total of 167 patients with cranial lesions. All were evaluated by plain radiography and computed tomography (CT). Nineteen variables in their medical records were reviewed. Logistic regression and neuronal network models were constructed and validated by the jackknife (leave-one-out) approach. The yields of the two models were compared by means of ROC curves, using the area under the curve as parameter. Seven men and 8 women presented hemangiomas. The mean age of these patients was 38.4 (15.4 years (mea ± standard deviation). Logistic regression identified as significant variables the shape, soft tissue mass and periosteal reaction. The neuronal network lent more importance to the existence of ossified matrix, ruptured cortical vein and the mixed calcified-blastic (trabeculated) pattern. The neuronal network showed a greater yield than logistic regression (Az, 0.9409) (0.004 versus 0.7211± 0.075; p<0.001). The neuronal network discloses hidden interactions among the variables, providing a higher yield in the characterization of cranial hemangiomas and constituting a medical diagnostic acid. (Author)29 refs

  20. CHARACTERIZING THE OPTICAL VARIABILITY OF BRIGHT BLAZARS: VARIABILITY-BASED SELECTION OF FERMI ACTIVE GALACTIC NUCLEI

    International Nuclear Information System (INIS)

    Ruan, John J.; Anderson, Scott F.; MacLeod, Chelsea L.; Becker, Andrew C.; Davenport, James R. A.; Ivezić, Željko; Burnett, T. H.; Kochanek, Christopher S.; Plotkin, Richard M.; Sesar, Branimir; Stuart, J. Scott

    2012-01-01

    We investigate the use of optical photometric variability to select and identify blazars in large-scale time-domain surveys, in part to aid in the identification of blazar counterparts to the ∼30% of γ-ray sources in the Fermi 2FGL catalog still lacking reliable associations. Using data from the optical LINEAR asteroid survey, we characterize the optical variability of blazars by fitting a damped random walk model to individual light curves with two main model parameters, the characteristic timescales of variability τ, and driving amplitudes on short timescales σ-circumflex. Imposing cuts on minimum τ and σ-circumflex allows for blazar selection with high efficiency E and completeness C. To test the efficacy of this approach, we apply this method to optically variable LINEAR objects that fall within the several-arcminute error ellipses of γ-ray sources in the Fermi 2FGL catalog. Despite the extreme stellar contamination at the shallow depth of the LINEAR survey, we are able to recover previously associated optical counterparts to Fermi active galactic nuclei with E ≥ 88% and C = 88% in Fermi 95% confidence error ellipses having semimajor axis r < 8'. We find that the suggested radio counterpart to Fermi source 2FGL J1649.6+5238 has optical variability consistent with other γ-ray blazars and is likely to be the γ-ray source. Our results suggest that the variability of the non-thermal jet emission in blazars is stochastic in nature, with unique variability properties due to the effects of relativistic beaming. After correcting for beaming, we estimate that the characteristic timescale of blazar variability is ∼3 years in the rest frame of the jet, in contrast with the ∼320 day disk flux timescale observed in quasars. The variability-based selection method presented will be useful for blazar identification in time-domain optical surveys and is also a probe of jet physics.

  1. Multiple Logistic Regression Analysis of Cigarette Use among High School Students

    Science.gov (United States)

    Adwere-Boamah, Joseph

    2011-01-01

    A binary logistic regression analysis was performed to predict high school students' cigarette smoking behavior from selected predictors from 2009 CDC Youth Risk Behavior Surveillance Survey. The specific target student behavior of interest was frequent cigarette use. Five predictor variables included in the model were: a) race, b) frequency of…

  2. Adaptive regression for modeling nonlinear relationships

    CERN Document Server

    Knafl, George J

    2016-01-01

    This book presents methods for investigating whether relationships are linear or nonlinear and for adaptively fitting appropriate models when they are nonlinear. Data analysts will learn how to incorporate nonlinearity in one or more predictor variables into regression models for different types of outcome variables. Such nonlinear dependence is often not considered in applied research, yet nonlinear relationships are common and so need to be addressed. A standard linear analysis can produce misleading conclusions, while a nonlinear analysis can provide novel insights into data, not otherwise possible. A variety of examples of the benefits of modeling nonlinear relationships are presented throughout the book. Methods are covered using what are called fractional polynomials based on real-valued power transformations of primary predictor variables combined with model selection based on likelihood cross-validation. The book covers how to formulate and conduct such adaptive fractional polynomial modeling in the s...

  3. Land use regression modeling of intra-urban residential variability in multiple traffic-related air pollutants

    Directory of Open Access Journals (Sweden)

    Baxter Lisa K

    2008-05-01

    Full Text Available Abstract Background There is a growing body of literature linking GIS-based measures of traffic density to asthma and other respiratory outcomes. However, no consensus exists on which traffic indicators best capture variability in different pollutants or within different settings. As part of a study on childhood asthma etiology, we examined variability in outdoor concentrations of multiple traffic-related air pollutants within urban communities, using a range of GIS-based predictors and land use regression techniques. Methods We measured fine particulate matter (PM2.5, nitrogen dioxide (NO2, and elemental carbon (EC outside 44 homes representing a range of traffic densities and neighborhoods across Boston, Massachusetts and nearby communities. Multiple three to four-day average samples were collected at each home during winters and summers from 2003 to 2005. Traffic indicators were derived using Massachusetts Highway Department data and direct traffic counts. Multivariate regression analyses were performed separately for each pollutant, using traffic indicators, land use, meteorology, site characteristics, and central site concentrations. Results PM2.5 was strongly associated with the central site monitor (R2 = 0.68. Additional variability was explained by total roadway length within 100 m of the home, smoking or grilling near the monitor, and block-group population density (R2 = 0.76. EC showed greater spatial variability, especially during winter months, and was predicted by roadway length within 200 m of the home. The influence of traffic was greater under low wind speed conditions, and concentrations were lower during summer (R2 = 0.52. NO2 showed significant spatial variability, predicted by population density and roadway length within 50 m of the home, modified by site characteristics (obstruction, and with higher concentrations during summer (R2 = 0.56. Conclusion Each pollutant examined displayed somewhat different spatial patterns

  4. On Weighted Support Vector Regression

    DEFF Research Database (Denmark)

    Han, Xixuan; Clemmensen, Line Katrine Harder

    2014-01-01

    We propose a new type of weighted support vector regression (SVR), motivated by modeling local dependencies in time and space in prediction of house prices. The classic weights of the weighted SVR are added to the slack variables in the objective function (OF‐weights). This procedure directly...... shrinks the coefficient of each observation in the estimated functions; thus, it is widely used for minimizing influence of outliers. We propose to additionally add weights to the slack variables in the constraints (CF‐weights) and call the combination of weights the doubly weighted SVR. We illustrate...... the differences and similarities of the two types of weights by demonstrating the connection between the Least Absolute Shrinkage and Selection Operator (LASSO) and the SVR. We show that an SVR problem can be transformed to a LASSO problem plus a linear constraint and a box constraint. We demonstrate...

  5. Variable selection for mixture and promotion time cure rate models.

    Science.gov (United States)

    Masud, Abdullah; Tu, Wanzhu; Yu, Zhangsheng

    2016-11-16

    Failure-time data with cured patients are common in clinical studies. Data from these studies are typically analyzed with cure rate models. Variable selection methods have not been well developed for cure rate models. In this research, we propose two least absolute shrinkage and selection operators based methods, for variable selection in mixture and promotion time cure models with parametric or nonparametric baseline hazards. We conduct an extensive simulation study to assess the operating characteristics of the proposed methods. We illustrate the use of the methods using data from a study of childhood wheezing. © The Author(s) 2016.

  6. Improved Variable Selection Algorithm Using a LASSO-Type Penalty, with an Application to Assessing Hepatitis B Infection Relevant Factors in Community Residents

    Science.gov (United States)

    Guo, Pi; Zeng, Fangfang; Hu, Xiaomin; Zhang, Dingmei; Zhu, Shuming; Deng, Yu; Hao, Yuantao

    2015-01-01

    Objectives In epidemiological studies, it is important to identify independent associations between collective exposures and a health outcome. The current stepwise selection technique ignores stochastic errors and suffers from a lack of stability. The alternative LASSO-penalized regression model can be applied to detect significant predictors from a pool of candidate variables. However, this technique is prone to false positives and tends to create excessive biases. It remains challenging to develop robust variable selection methods and enhance predictability. Material and methods Two improved algorithms denoted the two-stage hybrid and bootstrap ranking procedures, both using a LASSO-type penalty, were developed for epidemiological association analysis. The performance of the proposed procedures and other methods including conventional LASSO, Bolasso, stepwise and stability selection models were evaluated using intensive simulation. In addition, methods were compared by using an empirical analysis based on large-scale survey data of hepatitis B infection-relevant factors among Guangdong residents. Results The proposed procedures produced comparable or less biased selection results when compared to conventional variable selection models. In total, the two newly proposed procedures were stable with respect to various scenarios of simulation, demonstrating a higher power and a lower false positive rate during variable selection than the compared methods. In empirical analysis, the proposed procedures yielding a sparse set of hepatitis B infection-relevant factors gave the best predictive performance and showed that the procedures were able to select a more stringent set of factors. The individual history of hepatitis B vaccination, family and individual history of hepatitis B infection were associated with hepatitis B infection in the studied residents according to the proposed procedures. Conclusions The newly proposed procedures improve the identification of

  7. Enforcing Co-expression Within a Brain-Imaging Genomics Regression Framework.

    Science.gov (United States)

    Zille, Pascal; Calhoun, Vince D; Wang, Yu-Ping

    2017-06-28

    Among the challenges arising in brain imaging genetic studies, estimating the potential links between neurological and genetic variability within a population is key. In this work, we propose a multivariate, multimodal formulation for variable selection that leverages co-expression patterns across various data modalities. Our approach is based on an intuitive combination of two widely used statistical models: sparse regression and canonical correlation analysis (CCA). While the former seeks multivariate linear relationships between a given phenotype and associated observations, the latter searches to extract co-expression patterns between sets of variables belonging to different modalities. In the following, we propose to rely on a 'CCA-type' formulation in order to regularize the classical multimodal sparse regression problem (essentially incorporating both CCA and regression models within a unified formulation). The underlying motivation is to extract discriminative variables that are also co-expressed across modalities. We first show that the simplest formulation of such model can be expressed as a special case of collaborative learning methods. After discussing its limitation, we propose an extended, more flexible formulation, and introduce a simple and efficient alternating minimization algorithm to solve the associated optimization problem.We explore the parameter space and provide some guidelines regarding parameter selection. Both the original and extended versions are then compared on a simple toy dataset and a more advanced simulated imaging genomics dataset in order to illustrate the benefits of the latter. Finally, we validate the proposed formulation using single nucleotide polymorphisms (SNP) data and functional magnetic resonance imaging (fMRI) data from a population of adolescents (n = 362 subjects, age 16.9 ± 1.9 years from the Philadelphia Neurodevelopmental Cohort) for the study of learning ability. Furthermore, we carry out a significance

  8. From Rasch scores to regression

    DEFF Research Database (Denmark)

    Christensen, Karl Bang

    2006-01-01

    Rasch models provide a framework for measurement and modelling latent variables. Having measured a latent variable in a population a comparison of groups will often be of interest. For this purpose the use of observed raw scores will often be inadequate because these lack interval scale propertie....... This paper compares two approaches to group comparison: linear regression models using estimated person locations as outcome variables and latent regression models based on the distribution of the score....

  9. Multivariate modeling of complications with data driven variable selection: Guarding against overfitting and effects of data set size

    International Nuclear Information System (INIS)

    Schaaf, Arjen van der; Xu Chengjian; Luijk, Peter van; Veld, Aart A. van’t; Langendijk, Johannes A.; Schilstra, Cornelis

    2012-01-01

    Purpose: Multivariate modeling of complications after radiotherapy is frequently used in conjunction with data driven variable selection. This study quantifies the risk of overfitting in a data driven modeling method using bootstrapping for data with typical clinical characteristics, and estimates the minimum amount of data needed to obtain models with relatively high predictive power. Materials and methods: To facilitate repeated modeling and cross-validation with independent datasets for the assessment of true predictive power, a method was developed to generate simulated data with statistical properties similar to real clinical data sets. Characteristics of three clinical data sets from radiotherapy treatment of head and neck cancer patients were used to simulate data with set sizes between 50 and 1000 patients. A logistic regression method using bootstrapping and forward variable selection was used for complication modeling, resulting for each simulated data set in a selected number of variables and an estimated predictive power. The true optimal number of variables and true predictive power were calculated using cross-validation with very large independent data sets. Results: For all simulated data set sizes the number of variables selected by the bootstrapping method was on average close to the true optimal number of variables, but showed considerable spread. Bootstrapping is more accurate in selecting the optimal number of variables than the AIC and BIC alternatives, but this did not translate into a significant difference of the true predictive power. The true predictive power asymptotically converged toward a maximum predictive power for large data sets, and the estimated predictive power converged toward the true predictive power. More than half of the potential predictive power is gained after approximately 200 samples. Our simulations demonstrated severe overfitting (a predicative power lower than that of predicting 50% probability) in a number of small

  10. QSRR modeling for the chromatographic retention behavior of some β-lactam antibiotics using forward and firefly variable selection algorithms coupled with multiple linear regression.

    Science.gov (United States)

    Fouad, Marwa A; Tolba, Enas H; El-Shal, Manal A; El Kerdawy, Ahmed M

    2018-05-11

    The justified continuous emerging of new β-lactam antibiotics provokes the need for developing suitable analytical methods that accelerate and facilitate their analysis. A face central composite experimental design was adopted using different levels of phosphate buffer pH, acetonitrile percentage at zero time and after 15 min in a gradient program to obtain the optimum chromatographic conditions for the elution of 31 β-lactam antibiotics. Retention factors were used as the target property to build two QSRR models utilizing the conventional forward selection and the advanced nature-inspired firefly algorithm for descriptor selection, coupled with multiple linear regression. The obtained models showed high performance in both internal and external validation indicating their robustness and predictive ability. Williams-Hotelling test and student's t-test showed that there is no statistical significant difference between the models' results. Y-randomization validation showed that the obtained models are due to significant correlation between the selected molecular descriptors and the analytes' chromatographic retention. These results indicate that the generated FS-MLR and FFA-MLR models are showing comparable quality on both the training and validation levels. They also gave comparable information about the molecular features that influence the retention behavior of β-lactams under the current chromatographic conditions. We can conclude that in some cases simple conventional feature selection algorithm can be used to generate robust and predictive models comparable to that are generated using advanced ones. Copyright © 2018 Elsevier B.V. All rights reserved.

  11. Hierarchical regression analysis in structural Equation Modeling

    NARCIS (Netherlands)

    de Jong, P.F.

    1999-01-01

    In a hierarchical or fixed-order regression analysis, the independent variables are entered into the regression equation in a prespecified order. Such an analysis is often performed when the extra amount of variance accounted for in a dependent variable by a specific independent variable is the main

  12. Retro-regression--another important multivariate regression improvement.

    Science.gov (United States)

    Randić, M

    2001-01-01

    We review the serious problem associated with instabilities of the coefficients of regression equations, referred to as the MRA (multivariate regression analysis) "nightmare of the first kind". This is manifested when in a stepwise regression a descriptor is included or excluded from a regression. The consequence is an unpredictable change of the coefficients of the descriptors that remain in the regression equation. We follow with consideration of an even more serious problem, referred to as the MRA "nightmare of the second kind", arising when optimal descriptors are selected from a large pool of descriptors. This process typically causes at different steps of the stepwise regression a replacement of several previously used descriptors by new ones. We describe a procedure that resolves these difficulties. The approach is illustrated on boiling points of nonanes which are considered (1) by using an ordered connectivity basis; (2) by using an ordering resulting from application of greedy algorithm; and (3) by using an ordering derived from an exhaustive search for optimal descriptors. A novel variant of multiple regression analysis, called retro-regression (RR), is outlined showing how it resolves the ambiguities associated with both "nightmares" of the first and the second kind of MRA.

  13. Determinants of Non-Performing Assets in India - Panel Regression

    Directory of Open Access Journals (Sweden)

    Saikat Ghosh Roy

    2014-12-01

    Full Text Available It is well known that level of banks‟ credit plays an important role in economic developments. Indian banking sector has played a seminal role in supporting economic growth in India. Recently, Indian banks are experiencing consistent increase in non-performing assets (NPA. In this perspective, this paper investigates the trends in NPA in Indian banks and its determinants. The panel regressions, fixed effect allows evaluating the impact of selected macroeconomic variables on the NPA. The Panel regression result indicates that the GDP growth, change in exchange rate and global volatility have major effects on the NPA level of Indian banking sector.

  14. Regression analysis by example

    CERN Document Server

    Chatterjee, Samprit

    2012-01-01

    Praise for the Fourth Edition: ""This book is . . . an excellent source of examples for regression analysis. It has been and still is readily readable and understandable."" -Journal of the American Statistical Association Regression analysis is a conceptually simple method for investigating relationships among variables. Carrying out a successful application of regression analysis, however, requires a balance of theoretical results, empirical rules, and subjective judgment. Regression Analysis by Example, Fifth Edition has been expanded

  15. Applying Least Absolute Shrinkage Selection Operator and Akaike Information Criterion Analysis to Find the Best Multiple Linear Regression Models between Climate Indices and Components of Cow's Milk.

    Science.gov (United States)

    Marami Milani, Mohammad Reza; Hense, Andreas; Rahmani, Elham; Ploeger, Angelika

    2016-07-23

    This study focuses on multiple linear regression models relating six climate indices (temperature humidity THI, environmental stress ESI, equivalent temperature index ETI, heat load HLI, modified HLI (HLI new ), and respiratory rate predictor RRP) with three main components of cow's milk (yield, fat, and protein) for cows in Iran. The least absolute shrinkage selection operator (LASSO) and the Akaike information criterion (AIC) techniques are applied to select the best model for milk predictands with the smallest number of climate predictors. Uncertainty estimation is employed by applying bootstrapping through resampling. Cross validation is used to avoid over-fitting. Climatic parameters are calculated from the NASA-MERRA global atmospheric reanalysis. Milk data for the months from April to September, 2002 to 2010 are used. The best linear regression models are found in spring between milk yield as the predictand and THI, ESI, ETI, HLI, and RRP as predictors with p -value < 0.001 and R ² (0.50, 0.49) respectively. In summer, milk yield with independent variables of THI, ETI, and ESI show the highest relation ( p -value < 0.001) with R ² (0.69). For fat and protein the results are only marginal. This method is suggested for the impact studies of climate variability/change on agriculture and food science fields when short-time series or data with large uncertainty are available.

  16. Input variable selection for data-driven models of Coriolis flowmeters for two-phase flow measurement

    International Nuclear Information System (INIS)

    Wang, Lijuan; Yan, Yong; Wang, Xue; Wang, Tao

    2017-01-01

    Input variable selection is an essential step in the development of data-driven models for environmental, biological and industrial applications. Through input variable selection to eliminate the irrelevant or redundant variables, a suitable subset of variables is identified as the input of a model. Meanwhile, through input variable selection the complexity of the model structure is simplified and the computational efficiency is improved. This paper describes the procedures of the input variable selection for the data-driven models for the measurement of liquid mass flowrate and gas volume fraction under two-phase flow conditions using Coriolis flowmeters. Three advanced input variable selection methods, including partial mutual information (PMI), genetic algorithm-artificial neural network (GA-ANN) and tree-based iterative input selection (IIS) are applied in this study. Typical data-driven models incorporating support vector machine (SVM) are established individually based on the input candidates resulting from the selection methods. The validity of the selection outcomes is assessed through an output performance comparison of the SVM based data-driven models and sensitivity analysis. The validation and analysis results suggest that the input variables selected from the PMI algorithm provide more effective information for the models to measure liquid mass flowrate while the IIS algorithm provides a fewer but more effective variables for the models to predict gas volume fraction. (paper)

  17. Construction of multiple linear regression models using blood biomarkers for selecting against abdominal fat traits in broilers.

    Science.gov (United States)

    Dong, J Q; Zhang, X Y; Wang, S Z; Jiang, X F; Zhang, K; Ma, G W; Wu, M Q; Li, H; Zhang, H

    2018-01-01

    Plasma very low-density lipoprotein (VLDL) can be used to select for low body fat or abdominal fat (AF) in broilers, but its correlation with AF is limited. We investigated whether any other biochemical indicator can be used in combination with VLDL for a better selective effect. Nineteen plasma biochemical indicators were measured in male chickens from the Northeast Agricultural University broiler lines divergently selected for AF content (NEAUHLF) in the fed state at 46 and 48 d of age. The average concentration of every parameter for the 2 d was used for statistical analysis. Levels of these 19 plasma biochemical parameters were compared between the lean and fat lines. The phenotypic correlations between these plasma biochemical indicators and AF traits were analyzed. Then, multiple linear regression models were constructed to select the best model used for selecting against AF content. and the heritabilities of plasma indicators contained in the best models were estimated. The results showed that 11 plasma biochemical indicators (triglycerides, total bile acid, total protein, globulin, albumin/globulin, aspartate transaminase, alanine transaminase, gamma-glutamyl transpeptidase, uric acid, creatinine, and VLDL) differed significantly between the lean and fat lines (P linear regression models based on albumin/globulin, VLDL, triglycerides, globulin, total bile acid, and uric acid, had higher R2 (0.73) than the model based only on VLDL (0.21). The plasma parameters included in the best models had moderate heritability estimates (0.21 ≤ h2 ≤ 0.43). These results indicate that these multiple linear regression models can be used to select for lean broiler chickens. © 2017 Poultry Science Association Inc.

  18. Post-processing through linear regression

    Science.gov (United States)

    van Schaeybroeck, B.; Vannitsem, S.

    2011-03-01

    Various post-processing techniques are compared for both deterministic and ensemble forecasts, all based on linear regression between forecast data and observations. In order to evaluate the quality of the regression methods, three criteria are proposed, related to the effective correction of forecast error, the optimal variability of the corrected forecast and multicollinearity. The regression schemes under consideration include the ordinary least-square (OLS) method, a new time-dependent Tikhonov regularization (TDTR) method, the total least-square method, a new geometric-mean regression (GM), a recently introduced error-in-variables (EVMOS) method and, finally, a "best member" OLS method. The advantages and drawbacks of each method are clarified. These techniques are applied in the context of the 63 Lorenz system, whose model version is affected by both initial condition and model errors. For short forecast lead times, the number and choice of predictors plays an important role. Contrarily to the other techniques, GM degrades when the number of predictors increases. At intermediate lead times, linear regression is unable to provide corrections to the forecast and can sometimes degrade the performance (GM and the best member OLS with noise). At long lead times the regression schemes (EVMOS, TDTR) which yield the correct variability and the largest correlation between ensemble error and spread, should be preferred.

  19. Spatial Quantile Regression In Analysis Of Healthy Life Years In The European Union Countries

    Directory of Open Access Journals (Sweden)

    Trzpiot Grażyna

    2016-12-01

    Full Text Available The paper investigates the impact of the selected factors on the healthy life years of men and women in the EU countries. The multiple quantile spatial autoregression models are used in order to account for substantial differences in the healthy life years and life quality across the EU members. Quantile regression allows studying dependencies between variables in different quantiles of the response distribution. Moreover, this statistical tool is robust against violations of the classical regression assumption about the distribution of the error term. Parameters of the models were estimated using instrumental variable method (Kim, Muller 2004, whereas the confidence intervals and p-values were bootstrapped.

  20. Joint High-Dimensional Bayesian Variable and Covariance Selection with an Application to eQTL Analysis

    KAUST Repository

    Bhadra, Anindya

    2013-04-22

    We describe a Bayesian technique to (a) perform a sparse joint selection of significant predictor variables and significant inverse covariance matrix elements of the response variables in a high-dimensional linear Gaussian sparse seemingly unrelated regression (SSUR) setting and (b) perform an association analysis between the high-dimensional sets of predictors and responses in such a setting. To search the high-dimensional model space, where both the number of predictors and the number of possibly correlated responses can be larger than the sample size, we demonstrate that a marginalization-based collapsed Gibbs sampler, in combination with spike and slab type of priors, offers a computationally feasible and efficient solution. As an example, we apply our method to an expression quantitative trait loci (eQTL) analysis on publicly available single nucleotide polymorphism (SNP) and gene expression data for humans where the primary interest lies in finding the significant associations between the sets of SNPs and possibly correlated genetic transcripts. Our method also allows for inference on the sparse interaction network of the transcripts (response variables) after accounting for the effect of the SNPs (predictor variables). We exploit properties of Gaussian graphical models to make statements concerning conditional independence of the responses. Our method compares favorably to existing Bayesian approaches developed for this purpose. © 2013, The International Biometric Society.

  1. Gaussian process regression analysis for functional data

    CERN Document Server

    Shi, Jian Qing

    2011-01-01

    Gaussian Process Regression Analysis for Functional Data presents nonparametric statistical methods for functional regression analysis, specifically the methods based on a Gaussian process prior in a functional space. The authors focus on problems involving functional response variables and mixed covariates of functional and scalar variables.Covering the basics of Gaussian process regression, the first several chapters discuss functional data analysis, theoretical aspects based on the asymptotic properties of Gaussian process regression models, and new methodological developments for high dime

  2. Testing for marginal linear effects in quantile regression

    KAUST Repository

    Wang, Huixia Judy

    2017-10-23

    The paper develops a new marginal testing procedure to detect significant predictors that are associated with the conditional quantiles of a scalar response. The idea is to fit the marginal quantile regression on each predictor one at a time, and then to base the test on the t-statistics that are associated with the most predictive predictors. A resampling method is devised to calibrate this test statistic, which has non-regular limiting behaviour due to the selection of the most predictive variables. Asymptotic validity of the procedure is established in a general quantile regression setting in which the marginal quantile regression models can be misspecified. Even though a fixed dimension is assumed to derive the asymptotic results, the test proposed is applicable and computationally feasible for large dimensional predictors. The method is more flexible than existing marginal screening test methods based on mean regression and has the added advantage of being robust against outliers in the response. The approach is illustrated by using an application to a human immunodeficiency virus drug resistance data set.

  3. Testing for marginal linear effects in quantile regression

    KAUST Repository

    Wang, Huixia Judy; McKeague, Ian W.; Qian, Min

    2017-01-01

    The paper develops a new marginal testing procedure to detect significant predictors that are associated with the conditional quantiles of a scalar response. The idea is to fit the marginal quantile regression on each predictor one at a time, and then to base the test on the t-statistics that are associated with the most predictive predictors. A resampling method is devised to calibrate this test statistic, which has non-regular limiting behaviour due to the selection of the most predictive variables. Asymptotic validity of the procedure is established in a general quantile regression setting in which the marginal quantile regression models can be misspecified. Even though a fixed dimension is assumed to derive the asymptotic results, the test proposed is applicable and computationally feasible for large dimensional predictors. The method is more flexible than existing marginal screening test methods based on mean regression and has the added advantage of being robust against outliers in the response. The approach is illustrated by using an application to a human immunodeficiency virus drug resistance data set.

  4. A New Variable Selection Method Based on Mutual Information Maximization by Replacing Collinear Variables for Nonlinear Quantitative Structure-Property Relationship Models

    Energy Technology Data Exchange (ETDEWEB)

    Ghasemi, Jahan B.; Zolfonoun, Ehsan [Toosi University of Technology, Tehran (Korea, Republic of)

    2012-05-15

    Selection of the most informative molecular descriptors from the original data set is a key step for development of quantitative structure activity/property relationship models. Recently, mutual information (MI) has gained increasing attention in feature selection problems. This paper presents an effective mutual information-based feature selection approach, named mutual information maximization by replacing collinear variables (MIMRCV), for nonlinear quantitative structure-property relationship models. The proposed variable selection method was applied to three different QSPR datasets, soil degradation half-life of 47 organophosphorus pesticides, GC-MS retention times of 85 volatile organic compounds, and water-to-micellar cetyltrimethylammonium bromide partition coefficients of 62 organic compounds.The obtained results revealed that using MIMRCV as feature selection method improves the predictive quality of the developed models compared to conventional MI based variable selection algorithms.

  5. A New Variable Selection Method Based on Mutual Information Maximization by Replacing Collinear Variables for Nonlinear Quantitative Structure-Property Relationship Models

    International Nuclear Information System (INIS)

    Ghasemi, Jahan B.; Zolfonoun, Ehsan

    2012-01-01

    Selection of the most informative molecular descriptors from the original data set is a key step for development of quantitative structure activity/property relationship models. Recently, mutual information (MI) has gained increasing attention in feature selection problems. This paper presents an effective mutual information-based feature selection approach, named mutual information maximization by replacing collinear variables (MIMRCV), for nonlinear quantitative structure-property relationship models. The proposed variable selection method was applied to three different QSPR datasets, soil degradation half-life of 47 organophosphorus pesticides, GC-MS retention times of 85 volatile organic compounds, and water-to-micellar cetyltrimethylammonium bromide partition coefficients of 62 organic compounds.The obtained results revealed that using MIMRCV as feature selection method improves the predictive quality of the developed models compared to conventional MI based variable selection algorithms

  6. Beyond the mean estimate: a quantile regression analysis of inequalities in educational outcomes using INVALSI survey data

    Directory of Open Access Journals (Sweden)

    Antonella Costanzo

    2017-09-01

    Full Text Available Abstract The number of studies addressing issues of inequality in educational outcomes using cognitive achievement tests and variables from large-scale assessment data has increased. Here the value of using a quantile regression approach is compared with a classical regression analysis approach to study the relationships between educational outcomes and likely predictor variables. Italian primary school data from INVALSI large-scale assessments were analyzed using both quantile and standard regression approaches. Mathematics and reading scores were regressed on students' characteristics and geographical variables selected for their theoretical and policy relevance. The results demonstrated that, in Italy, the role of gender and immigrant status varied across the entire conditional distribution of students’ performance. Analogous results emerged pertaining to the difference in students’ performance across Italian geographic areas. These findings suggest that quantile regression analysis is a useful tool to explore the determinants and mechanisms of inequality in educational outcomes. A proper interpretation of quantile estimates may enable teachers to identify effective learning activities and help policymakers to develop tailored programs that increase equity in education.

  7. Prediction of radiation levels in residences: A methodological comparison of CART [Classification and Regression Tree Analysis] and conventional regression

    International Nuclear Information System (INIS)

    Janssen, I.; Stebbings, J.H.

    1990-01-01

    In environmental epidemiology, trace and toxic substance concentrations frequently have very highly skewed distributions ranging over one or more orders of magnitude, and prediction by conventional regression is often poor. Classification and Regression Tree Analysis (CART) is an alternative in such contexts. To compare the techniques, two Pennsylvania data sets and three independent variables are used: house radon progeny (RnD) and gamma levels as predicted by construction characteristics in 1330 houses; and ∼200 house radon (Rn) measurements as predicted by topographic parameters. CART may identify structural variables of interest not identified by conventional regression, and vice versa, but in general the regression models are similar. CART has major advantages in dealing with other common characteristics of environmental data sets, such as missing values, continuous variables requiring transformations, and large sets of potential independent variables. CART is most useful in the identification and screening of independent variables, greatly reducing the need for cross-tabulations and nested breakdown analyses. There is no need to discard cases with missing values for the independent variables because surrogate variables are intrinsic to CART. The tree-structured approach is also independent of the scale on which the independent variables are measured, so that transformations are unnecessary. CART identifies important interactions as well as main effects. The major advantages of CART appear to be in exploring data. Once the important variables are identified, conventional regressions seem to lead to results similar but more interpretable by most audiences. 12 refs., 8 figs., 10 tabs

  8. Post-processing through linear regression

    Directory of Open Access Journals (Sweden)

    B. Van Schaeybroeck

    2011-03-01

    Full Text Available Various post-processing techniques are compared for both deterministic and ensemble forecasts, all based on linear regression between forecast data and observations. In order to evaluate the quality of the regression methods, three criteria are proposed, related to the effective correction of forecast error, the optimal variability of the corrected forecast and multicollinearity. The regression schemes under consideration include the ordinary least-square (OLS method, a new time-dependent Tikhonov regularization (TDTR method, the total least-square method, a new geometric-mean regression (GM, a recently introduced error-in-variables (EVMOS method and, finally, a "best member" OLS method. The advantages and drawbacks of each method are clarified.

    These techniques are applied in the context of the 63 Lorenz system, whose model version is affected by both initial condition and model errors. For short forecast lead times, the number and choice of predictors plays an important role. Contrarily to the other techniques, GM degrades when the number of predictors increases. At intermediate lead times, linear regression is unable to provide corrections to the forecast and can sometimes degrade the performance (GM and the best member OLS with noise. At long lead times the regression schemes (EVMOS, TDTR which yield the correct variability and the largest correlation between ensemble error and spread, should be preferred.

  9. Variable selection based on clustering analysis for improvement of polyphenols prediction in green tea using synchronous fluorescence spectra

    Science.gov (United States)

    Shan, Jiajia; Wang, Xue; Zhou, Hao; Han, Shuqing; Riza, Dimas Firmanda Al; Kondo, Naoshi

    2018-04-01

    Synchronous fluorescence spectra, combined with multivariate analysis were used to predict flavonoids content in green tea rapidly and nondestructively. This paper presented a new and efficient spectral intervals selection method called clustering based partial least square (CL-PLS), which selected informative wavelengths by combining clustering concept and partial least square (PLS) methods to improve models’ performance by synchronous fluorescence spectra. The fluorescence spectra of tea samples were obtained and k-means and kohonen-self organizing map clustering algorithms were carried out to cluster full spectra into several clusters, and sub-PLS regression model was developed on each cluster. Finally, CL-PLS models consisting of gradually selected clusters were built. Correlation coefficient (R) was used to evaluate the effect on prediction performance of PLS models. In addition, variable influence on projection partial least square (VIP-PLS), selectivity ratio partial least square (SR-PLS), interval partial least square (iPLS) models and full spectra PLS model were investigated and the results were compared. The results showed that CL-PLS presented the best result for flavonoids prediction using synchronous fluorescence spectra.

  10. Correlation and simple linear regression.

    Science.gov (United States)

    Zou, Kelly H; Tuncali, Kemal; Silverman, Stuart G

    2003-06-01

    In this tutorial article, the concepts of correlation and regression are reviewed and demonstrated. The authors review and compare two correlation coefficients, the Pearson correlation coefficient and the Spearman rho, for measuring linear and nonlinear relationships between two continuous variables. In the case of measuring the linear relationship between a predictor and an outcome variable, simple linear regression analysis is conducted. These statistical concepts are illustrated by using a data set from published literature to assess a computed tomography-guided interventional technique. These statistical methods are important for exploring the relationships between variables and can be applied to many radiologic studies.

  11. Relation between sick leave and selected exposure variables among women semiconductor workers in Malaysia

    Science.gov (United States)

    Chee, H; Rampal, K

    2003-01-01

    Aims: To determine the relation between sick leave and selected exposure variables among women semiconductor workers. Methods: This was a cross sectional survey of production workers from 18 semiconductor factories. Those selected had to be women, direct production operators up to the level of line leader, and Malaysian citizens. Sick leave and exposure to physical and chemical hazards were determined by self reporting. Three sick leave variables were used; number of sick leave days taken in the past year was the variable of interest in logistic regression models where the effects of age, marital status, work task, work schedule, work section, and duration of work in factory and work section were also explored. Results: Marital status was strongly linked to the taking of sick leave. Age, work schedule, and duration of work in the factory were significant confounders only in certain cases. After adjusting for these confounders, chemical and physical exposures, with the exception of poor ventilation and smelling chemicals, showed no significant relation to the taking of sick leave within the past year. Work section was a good predictor for taking sick leave, as wafer polishing workers faced higher odds of taking sick leave for each of the three cut off points of seven days, three days, and not at all, while parts assembly workers also faced significantly higher odds of taking sick leave. Conclusion: In Malaysia, the wafer fabrication factories only carry out a limited portion of the work processes, in particular, wafer polishing and the processes immediately prior to and following it. This study, in showing higher illness rates for workers in wafer polishing compared to semiconductor assembly, has implications for the governmental policy of encouraging the setting up of wafer fabrication plants with the full range of work processes. PMID:12660374

  12. Statistical identification of effective input variables

    International Nuclear Information System (INIS)

    Vaurio, J.K.

    1982-09-01

    A statistical sensitivity analysis procedure has been developed for ranking the input data of large computer codes in the order of sensitivity-importance. The method is economical for large codes with many input variables, since it uses a relatively small number of computer runs. No prior judgemental elimination of input variables is needed. The sceening method is based on stagewise correlation and extensive regression analysis of output values calculated with selected input value combinations. The regression process deals with multivariate nonlinear functions, and statistical tests are also available for identifying input variables that contribute to threshold effects, i.e., discontinuities in the output variables. A computer code SCREEN has been developed for implementing the screening techniques. The efficiency has been demonstrated by several examples and applied to a fast reactor safety analysis code (Venus-II). However, the methods and the coding are general and not limited to such applications

  13. A gentle introduction to quantile regression for ecologists

    Science.gov (United States)

    Cade, B.S.; Noon, B.R.

    2003-01-01

    Quantile regression is a way to estimate the conditional quantiles of a response variable distribution in the linear model that provides a more complete view of possible causal relationships between variables in ecological processes. Typically, all the factors that affect ecological processes are not measured and included in the statistical models used to investigate relationships between variables associated with those processes. As a consequence, there may be a weak or no predictive relationship between the mean of the response variable (y) distribution and the measured predictive factors (X). Yet there may be stronger, useful predictive relationships with other parts of the response variable distribution. This primer relates quantile regression estimates to prediction intervals in parametric error distribution regression models (eg least squares), and discusses the ordering characteristics, interval nature, sampling variation, weighting, and interpretation of the estimates for homogeneous and heterogeneous regression models.

  14. Portfolio Selection Based on Distance between Fuzzy Variables

    Directory of Open Access Journals (Sweden)

    Weiyi Qian

    2014-01-01

    Full Text Available This paper researches portfolio selection problem in fuzzy environment. We introduce a new simple method in which the distance between fuzzy variables is used to measure the divergence of fuzzy investment return from a prior one. Firstly, two new mathematical models are proposed by expressing divergence as distance, investment return as expected value, and risk as variance and semivariance, respectively. Secondly, the crisp forms of the new models are also provided for different types of fuzzy variables. Finally, several numerical examples are given to illustrate the effectiveness of the proposed approach.

  15. A Comparative Investigation of the Combined Effects of Pre-Processing, Wavelength Selection, and Regression Methods on Near-Infrared Calibration Model Performance.

    Science.gov (United States)

    Wan, Jian; Chen, Yi-Chieh; Morris, A Julian; Thennadil, Suresh N

    2017-07-01

    Near-infrared (NIR) spectroscopy is being widely used in various fields ranging from pharmaceutics to the food industry for analyzing chemical and physical properties of the substances concerned. Its advantages over other analytical techniques include available physical interpretation of spectral data, nondestructive nature and high speed of measurements, and little or no need for sample preparation. The successful application of NIR spectroscopy relies on three main aspects: pre-processing of spectral data to eliminate nonlinear variations due to temperature, light scattering effects and many others, selection of those wavelengths that contribute useful information, and identification of suitable calibration models using linear/nonlinear regression . Several methods have been developed for each of these three aspects and many comparative studies of different methods exist for an individual aspect or some combinations. However, there is still a lack of comparative studies for the interactions among these three aspects, which can shed light on what role each aspect plays in the calibration and how to combine various methods of each aspect together to obtain the best calibration model. This paper aims to provide such a comparative study based on four benchmark data sets using three typical pre-processing methods, namely, orthogonal signal correction (OSC), extended multiplicative signal correction (EMSC) and optical path-length estimation and correction (OPLEC); two existing wavelength selection methods, namely, stepwise forward selection (SFS) and genetic algorithm optimization combined with partial least squares regression for spectral data (GAPLSSP); four popular regression methods, namely, partial least squares (PLS), least absolute shrinkage and selection operator (LASSO), least squares support vector machine (LS-SVM), and Gaussian process regression (GPR). The comparative study indicates that, in general, pre-processing of spectral data can play a significant

  16. Entrepreneurial intention modeling using hierarchical multiple regression

    Directory of Open Access Journals (Sweden)

    Marina Jeger

    2014-12-01

    Full Text Available The goal of this study is to identify the contribution of effectuation dimensions to the predictive power of the entrepreneurial intention model over and above that which can be accounted for by other predictors selected and confirmed in previous studies. As is often the case in social and behavioral studies, some variables are likely to be highly correlated with each other. Therefore, the relative amount of variance in the criterion variable explained by each of the predictors depends on several factors such as the order of variable entry and sample specifics. The results show the modest predictive power of two dimensions of effectuation prior to the introduction of the theory of planned behavior elements. The article highlights the main advantages of applying hierarchical regression in social sciences as well as in the specific context of entrepreneurial intention formation, and addresses some of the potential pitfalls that this type of analysis entails.

  17. Genetic algorithm as a variable selection procedure for the simulation of 13C nuclear magnetic resonance spectra of flavonoid derivatives using multiple linear regression.

    Science.gov (United States)

    Ghavami, Raoof; Najafi, Amir; Sajadi, Mohammad; Djannaty, Farhad

    2008-09-01

    In order to accurately simulate (13)C NMR spectra of hydroxy, polyhydroxy and methoxy substituted flavonoid a quantitative structure-property relationship (QSPR) model, relating atom-based calculated descriptors to (13)C NMR chemical shifts (ppm, TMS=0), is developed. A dataset consisting of 50 flavonoid derivatives was employed for the present analysis. A set of 417 topological, geometrical, and electronic descriptors representing various structural characteristics was calculated and separate multilinear QSPR models were developed between each carbon atom of flavonoid and the calculated descriptors. Genetic algorithm (GA) and multiple linear regression analysis (MLRA) were used to select the descriptors and to generate the correlation models. Analysis of the results revealed a correlation coefficient and root mean square error (RMSE) of 0.994 and 2.53ppm, respectively, for the prediction set.

  18. Applied Regression Modeling A Business Approach

    CERN Document Server

    Pardoe, Iain

    2012-01-01

    An applied and concise treatment of statistical regression techniques for business students and professionals who have little or no background in calculusRegression analysis is an invaluable statistical methodology in business settings and is vital to model the relationship between a response variable and one or more predictor variables, as well as the prediction of a response value given values of the predictors. In view of the inherent uncertainty of business processes, such as the volatility of consumer spending and the presence of market uncertainty, business professionals use regression a

  19. A New Variable Weighting and Selection Procedure for K-Means Cluster Analysis

    Science.gov (United States)

    Steinley, Douglas; Brusco, Michael J.

    2008-01-01

    A variance-to-range ratio variable weighting procedure is proposed. We show how this weighting method is theoretically grounded in the inherent variability found in data exhibiting cluster structure. In addition, a variable selection procedure is proposed to operate in conjunction with the variable weighting technique. The performances of these…

  20. Punishment induced behavioural and neurophysiological variability reveals dopamine-dependent selection of kinematic movement parameters

    Science.gov (United States)

    Galea, Joseph M.; Ruge, Diane; Buijink, Arthur; Bestmann, Sven; Rothwell, John C.

    2013-01-01

    Action selection describes the high-level process which selects between competing movements. In animals, behavioural variability is critical for the motor exploration required to select the action which optimizes reward and minimizes cost/punishment, and is guided by dopamine (DA). The aim of this study was to test in humans whether low-level movement parameters are affected by punishment and reward in ways similar to high-level action selection. Moreover, we addressed the proposed dependence of behavioural and neurophysiological variability on DA, and whether this may underpin the exploration of kinematic parameters. Participants performed an out-and-back index finger movement and were instructed that monetary reward and punishment were based on its maximal acceleration (MA). In fact, the feedback was not contingent on the participant’s behaviour but pre-determined. Blocks highly-biased towards punishment were associated with increased MA variability relative to blocks with either reward or without feedback. This increase in behavioural variability was positively correlated with neurophysiological variability, as measured by changes in cortico-spinal excitability with transcranial magnetic stimulation over the primary motor cortex. Following the administration of a DA-antagonist, the variability associated with punishment diminished and the correlation between behavioural and neurophysiological variability no longer existed. Similar changes in variability were not observed when participants executed a pre-determined MA, nor did DA influence resting neurophysiological variability. Thus, under conditions of punishment, DA-dependent processes influence the selection of low-level movement parameters. We propose that the enhanced behavioural variability reflects the exploration of kinematic parameters for less punishing, or conversely more rewarding, outcomes. PMID:23447607

  1. A Simulation Investigation of Principal Component Regression.

    Science.gov (United States)

    Allen, David E.

    Regression analysis is one of the more common analytic tools used by researchers. However, multicollinearity between the predictor variables can cause problems in using the results of regression analyses. Problems associated with multicollinearity include entanglement of relative influences of variables due to reduced precision of estimation,…

  2. Measurement error in epidemiologic studies of air pollution based on land-use regression models.

    Science.gov (United States)

    Basagaña, Xavier; Aguilera, Inmaculada; Rivera, Marcela; Agis, David; Foraster, Maria; Marrugat, Jaume; Elosua, Roberto; Künzli, Nino

    2013-10-15

    Land-use regression (LUR) models are increasingly used to estimate air pollution exposure in epidemiologic studies. These models use air pollution measurements taken at a small set of locations and modeling based on geographical covariates for which data are available at all study participant locations. The process of LUR model development commonly includes a variable selection procedure. When LUR model predictions are used as explanatory variables in a model for a health outcome, measurement error can lead to bias of the regression coefficients and to inflation of their variance. In previous studies dealing with spatial predictions of air pollution, bias was shown to be small while most of the effect of measurement error was on the variance. In this study, we show that in realistic cases where LUR models are applied to health data, bias in health-effect estimates can be substantial. This bias depends on the number of air pollution measurement sites, the number of available predictors for model selection, and the amount of explainable variability in the true exposure. These results should be taken into account when interpreting health effects from studies that used LUR models.

  3. Curve fitting and modeling with splines using statistical variable selection techniques

    Science.gov (United States)

    Smith, P. L.

    1982-01-01

    The successful application of statistical variable selection techniques to fit splines is demonstrated. Major emphasis is given to knot selection, but order determination is also discussed. Two FORTRAN backward elimination programs, using the B-spline basis, were developed. The program for knot elimination is compared in detail with two other spline-fitting methods and several statistical software packages. An example is also given for the two-variable case using a tensor product basis, with a theoretical discussion of the difficulties of their use.

  4. A Quantile Regression Approach to Estimating the Distribution of Anesthetic Procedure Time during Induction.

    Directory of Open Access Journals (Sweden)

    Hsin-Lun Wu

    Full Text Available Although procedure time analyses are important for operating room management, it is not easy to extract useful information from clinical procedure time data. A novel approach was proposed to analyze procedure time during anesthetic induction. A two-step regression analysis was performed to explore influential factors of anesthetic induction time (AIT. Linear regression with stepwise model selection was used to select significant correlates of AIT and then quantile regression was employed to illustrate the dynamic relationships between AIT and selected variables at distinct quantiles. A total of 1,060 patients were analyzed. The first and second-year residents (R1-R2 required longer AIT than the third and fourth-year residents and attending anesthesiologists (p = 0.006. Factors prolonging AIT included American Society of Anesthesiologist physical status ≧ III, arterial, central venous and epidural catheterization, and use of bronchoscopy. Presence of surgeon before induction would decrease AIT (p < 0.001. Types of surgery also had significant influence on AIT. Quantile regression satisfactorily estimated extra time needed to complete induction for each influential factor at distinct quantiles. Our analysis on AIT demonstrated the benefit of quantile regression analysis to provide more comprehensive view of the relationships between procedure time and related factors. This novel two-step regression approach has potential applications to procedure time analysis in operating room management.

  5. Modeling Governance KB with CATPCA to Overcome Multicollinearity in the Logistic Regression

    Science.gov (United States)

    Khikmah, L.; Wijayanto, H.; Syafitri, U. D.

    2017-04-01

    The problem often encounters in logistic regression modeling are multicollinearity problems. Data that have multicollinearity between explanatory variables with the result in the estimation of parameters to be bias. Besides, the multicollinearity will result in error in the classification. In general, to overcome multicollinearity in regression used stepwise regression. They are also another method to overcome multicollinearity which involves all variable for prediction. That is Principal Component Analysis (PCA). However, classical PCA in only for numeric data. Its data are categorical, one method to solve the problems is Categorical Principal Component Analysis (CATPCA). Data were used in this research were a part of data Demographic and Population Survey Indonesia (IDHS) 2012. This research focuses on the characteristic of women of using the contraceptive methods. Classification results evaluated using Area Under Curve (AUC) values. The higher the AUC value, the better. Based on AUC values, the classification of the contraceptive method using stepwise method (58.66%) is better than the logistic regression model (57.39%) and CATPCA (57.39%). Evaluation of the results of logistic regression using sensitivity, shows the opposite where CATPCA method (99.79%) is better than logistic regression method (92.43%) and stepwise (92.05%). Therefore in this study focuses on major class classification (using a contraceptive method), then the selected model is CATPCA because it can raise the level of the major class model accuracy.

  6. Sparse Regression by Projection and Sparse Discriminant Analysis

    KAUST Repository

    Qi, Xin

    2015-04-03

    © 2015, © American Statistical Association, Institute of Mathematical Statistics, and Interface Foundation of North America. Recent years have seen active developments of various penalized regression methods, such as LASSO and elastic net, to analyze high-dimensional data. In these approaches, the direction and length of the regression coefficients are determined simultaneously. Due to the introduction of penalties, the length of the estimates can be far from being optimal for accurate predictions. We introduce a new framework, regression by projection, and its sparse version to analyze high-dimensional data. The unique nature of this framework is that the directions of the regression coefficients are inferred first, and the lengths and the tuning parameters are determined by a cross-validation procedure to achieve the largest prediction accuracy. We provide a theoretical result for simultaneous model selection consistency and parameter estimation consistency of our method in high dimension. This new framework is then generalized such that it can be applied to principal components analysis, partial least squares, and canonical correlation analysis. We also adapt this framework for discriminant analysis. Compared with the existing methods, where there is relatively little control of the dependency among the sparse components, our method can control the relationships among the components. We present efficient algorithms and related theory for solving the sparse regression by projection problem. Based on extensive simulations and real data analysis, we demonstrate that our method achieves good predictive performance and variable selection in the regression setting, and the ability to control relationships between the sparse components leads to more accurate classification. In supplementary materials available online, the details of the algorithms and theoretical proofs, and R codes for all simulation studies are provided.

  7. Multiple regression analysis of anthropometric measurements influencing the cephalic index of male Japanese university students.

    Science.gov (United States)

    Hossain, Md Golam; Saw, Aik; Alam, Rashidul; Ohtsuki, Fumio; Kamarul, Tunku

    2013-09-01

    Cephalic index (CI), the ratio of head breadth to head length, is widely used to categorise human populations. The aim of this study was to access the impact of anthropometric measurements on the CI of male Japanese university students. This study included 1,215 male university students from Tokyo and Kyoto, selected using convenient sampling. Multiple regression analysis was used to determine the effect of anthropometric measurements on CI. The variance inflation factor (VIF) showed no evidence of a multicollinearity problem among independent variables. The coefficients of the regression line demonstrated a significant positive relationship between CI and minimum frontal breadth (p regression analysis showed a greater likelihood for minimum frontal breadth (p regression analysis revealed bizygomatic breadth, head circumference, minimum frontal breadth, head height and morphological facial height to be the best predictor craniofacial measurements with respect to CI. The results suggest that most of the variables considered in this study appear to influence the CI of adult male Japanese students.

  8. Regression analysis with categorized regression calibrated exposure: some interesting findings

    Directory of Open Access Journals (Sweden)

    Hjartåker Anette

    2006-07-01

    Full Text Available Abstract Background Regression calibration as a method for handling measurement error is becoming increasingly well-known and used in epidemiologic research. However, the standard version of the method is not appropriate for exposure analyzed on a categorical (e.g. quintile scale, an approach commonly used in epidemiologic studies. A tempting solution could then be to use the predicted continuous exposure obtained through the regression calibration method and treat it as an approximation to the true exposure, that is, include the categorized calibrated exposure in the main regression analysis. Methods We use semi-analytical calculations and simulations to evaluate the performance of the proposed approach compared to the naive approach of not correcting for measurement error, in situations where analyses are performed on quintile scale and when incorporating the original scale into the categorical variables, respectively. We also present analyses of real data, containing measures of folate intake and depression, from the Norwegian Women and Cancer study (NOWAC. Results In cases where extra information is available through replicated measurements and not validation data, regression calibration does not maintain important qualities of the true exposure distribution, thus estimates of variance and percentiles can be severely biased. We show that the outlined approach maintains much, in some cases all, of the misclassification found in the observed exposure. For that reason, regression analysis with the corrected variable included on a categorical scale is still biased. In some cases the corrected estimates are analytically equal to those obtained by the naive approach. Regression calibration is however vastly superior to the naive method when applying the medians of each category in the analysis. Conclusion Regression calibration in its most well-known form is not appropriate for measurement error correction when the exposure is analyzed on a

  9. Introduction to the use of regression models in epidemiology.

    Science.gov (United States)

    Bender, Ralf

    2009-01-01

    Regression modeling is one of the most important statistical techniques used in analytical epidemiology. By means of regression models the effect of one or several explanatory variables (e.g., exposures, subject characteristics, risk factors) on a response variable such as mortality or cancer can be investigated. From multiple regression models, adjusted effect estimates can be obtained that take the effect of potential confounders into account. Regression methods can be applied in all epidemiologic study designs so that they represent a universal tool for data analysis in epidemiology. Different kinds of regression models have been developed in dependence on the measurement scale of the response variable and the study design. The most important methods are linear regression for continuous outcomes, logistic regression for binary outcomes, Cox regression for time-to-event data, and Poisson regression for frequencies and rates. This chapter provides a nontechnical introduction to these regression models with illustrating examples from cancer research.

  10. Predicting blood β-hydroxybutyrate using milk Fourier transform infrared spectrum, milk composition, and producer-reported variables with multiple linear regression, partial least squares regression, and artificial neural network.

    Science.gov (United States)

    Pralle, R S; Weigel, K W; White, H M

    2018-05-01

    Prediction of postpartum hyperketonemia (HYK) using Fourier transform infrared (FTIR) spectrometry analysis could be a practical diagnostic option for farms because these data are now available from routine milk analysis during Dairy Herd Improvement testing. The objectives of this study were to (1) develop and evaluate blood β-hydroxybutyrate (BHB) prediction models using multivariate linear regression (MLR), partial least squares regression (PLS), and artificial neural network (ANN) methods and (2) evaluate whether milk FTIR spectrum (mFTIR)-based models are improved with the inclusion of test-day variables (mTest; milk composition and producer-reported data). Paired blood and milk samples were collected from multiparous cows 5 to 18 d postpartum at 3 Wisconsin farms (3,629 observations from 1,013 cows). Blood BHB concentration was determined by a Precision Xtra meter (Abbot Diabetes Care, Alameda, CA), and milk samples were analyzed by a privately owned laboratory (AgSource, Menomonie, WI) for components and FTIR spectrum absorbance. Producer-recorded variables were extracted from farm management software. A blood BHB ≥1.2 mmol/L was considered HYK. The data set was divided into a training set (n = 3,020) and an external testing set (n = 609). Model fitting was implemented with JMP 12 (SAS Institute, Cary, NC). A 5-fold cross-validation was performed on the training data set for the MLR, PLS, and ANN prediction methods, with square root of blood BHB as the dependent variable. Each method was fitted using 3 combinations of variables: mFTIR, mTest, or mTest + mFTIR variables. Models were evaluated based on coefficient of determination, root mean squared error, and area under the receiver operating characteristic curve. Four models (PLS-mTest + mFTIR, ANN-mFTIR, ANN-mTest, and ANN-mTest + mFTIR) were chosen for further evaluation in the testing set after fitting to the full training set. In the cross-validation analysis, model fit was greatest for ANN, followed

  11. A Seemingly Unrelated Poisson Regression Model

    OpenAIRE

    King, Gary

    1989-01-01

    This article introduces a new estimator for the analysis of two contemporaneously correlated endogenous event count variables. This seemingly unrelated Poisson regression model (SUPREME) estimator combines the efficiencies created by single equation Poisson regression model estimators and insights from "seemingly unrelated" linear regression models.

  12. A Time-Series Water Level Forecasting Model Based on Imputation and Variable Selection Method.

    Science.gov (United States)

    Yang, Jun-He; Cheng, Ching-Hsue; Chan, Chia-Pan

    2017-01-01

    Reservoirs are important for households and impact the national economy. This paper proposed a time-series forecasting model based on estimating a missing value followed by variable selection to forecast the reservoir's water level. This study collected data from the Taiwan Shimen Reservoir as well as daily atmospheric data from 2008 to 2015. The two datasets are concatenated into an integrated dataset based on ordering of the data as a research dataset. The proposed time-series forecasting model summarily has three foci. First, this study uses five imputation methods to directly delete the missing value. Second, we identified the key variable via factor analysis and then deleted the unimportant variables sequentially via the variable selection method. Finally, the proposed model uses a Random Forest to build the forecasting model of the reservoir's water level. This was done to compare with the listing method under the forecasting error. These experimental results indicate that the Random Forest forecasting model when applied to variable selection with full variables has better forecasting performance than the listing model. In addition, this experiment shows that the proposed variable selection can help determine five forecast methods used here to improve the forecasting capability.

  13. Using Random Forests to Select Optimal Input Variables for Short-Term Wind Speed Forecasting Models

    Directory of Open Access Journals (Sweden)

    Hui Wang

    2017-10-01

    Full Text Available Achieving relatively high-accuracy short-term wind speed forecasting estimates is a precondition for the construction and grid-connected operation of wind power forecasting systems for wind farms. Currently, most research is focused on the structure of forecasting models and does not consider the selection of input variables, which can have significant impacts on forecasting performance. This paper presents an input variable selection method for wind speed forecasting models. The candidate input variables for various leading periods are selected and random forests (RF is employed to evaluate the importance of all variable as features. The feature subset with the best evaluation performance is selected as the optimal feature set. Then, kernel-based extreme learning machine is constructed to evaluate the performance of input variables selection based on RF. The results of the case study show that by removing the uncorrelated and redundant features, RF effectively extracts the most strongly correlated set of features from the candidate input variables. By finding the optimal feature combination to represent the original information, RF simplifies the structure of the wind speed forecasting model, shortens the training time required, and substantially improves the model’s accuracy and generalization ability, demonstrating that the input variables selected by RF are effective.

  14. Predicting hyperketonemia by logistic and linear regression using test-day milk and performance variables in early-lactation Holstein and Jersey cows.

    Science.gov (United States)

    Chandler, T L; Pralle, R S; Dórea, J R R; Poock, S E; Oetzel, G R; Fourdraine, R H; White, H M

    2018-03-01

    Although cowside testing strategies for diagnosing hyperketonemia (HYK) are available, many are labor intensive and costly, and some lack sufficient accuracy. Predicting milk ketone bodies by Fourier transform infrared spectrometry during routine milk sampling may offer a more practical monitoring strategy. The objectives of this study were to (1) develop linear and logistic regression models using all available test-day milk and performance variables for predicting HYK and (2) compare prediction methods (Fourier transform infrared milk ketone bodies, linear regression models, and logistic regression models) to determine which is the most predictive of HYK. Given the data available, a secondary objective was to evaluate differences in test-day milk and performance variables (continuous measurements) between Holsteins and Jerseys and between cows with or without HYK within breed. Blood samples were collected on the same day as milk sampling from 658 Holstein and 468 Jersey cows between 5 and 20 d in milk (DIM). Diagnosis of HYK was at a serum β-hydroxybutyrate (BHB) concentration ≥1.2 mmol/L. Concentrations of milk BHB and acetone were predicted by Fourier transform infrared spectrometry (Foss Analytical, Hillerød, Denmark). Thresholds of milk BHB and acetone were tested for diagnostic accuracy, and logistic models were built from continuous variables to predict HYK in primiparous and multiparous cows within breed. Linear models were constructed from continuous variables for primiparous and multiparous cows within breed that were 5 to 11 DIM or 12 to 20 DIM. Milk ketone body thresholds diagnosed HYK with 64.0 to 92.9% accuracy in Holsteins and 59.1 to 86.6% accuracy in Jerseys. Logistic models predicted HYK with 82.6 to 97.3% accuracy. Internally cross-validated multiple linear regression models diagnosed HYK of Holstein cows with 97.8% accuracy for primiparous and 83.3% accuracy for multiparous cows. Accuracy of Jersey models was 81.3% in primiparous and 83

  15. Ethnic variability in adiposity and cardiovascular risk: the variable disease selection hypothesis.

    Science.gov (United States)

    Wells, Jonathan C K

    2009-02-01

    Evidence increasingly suggests that ethnic differences in cardiovascular risk are partly mediated by adipose tissue biology, which refers to the regional distribution of adipose tissue and its differential metabolic activity. This paper proposes a novel evolutionary hypothesis for ethnic genetic variability in adipose tissue biology. Whereas medical interest focuses on the harmful effect of excess fat, the value of adipose tissue is greatest during chronic energy insufficiency. Following Neel's influential paper on the thrifty genotype, proposed to have been favoured by exposure to cycles of feast and famine, much effort has been devoted to searching for genetic markers of 'thrifty metabolism'. However, whether famine-induced starvation was the primary selective pressure on adipose tissue biology has been questioned, while the notion that fat primarily represents a buffer against starvation appears inconsistent with historical records of mortality during famines. This paper reviews evidence for the role played by adipose tissue in immune function and proposes that adipose tissue biology responds to selective pressures acting through infectious disease. Different diseases activate the immune system in different ways and induce different metabolic costs. It is hypothesized that exposure to different infectious disease burdens has favoured ethnic genetic variability in the anatomical location of, and metabolic profile of, adipose tissue depots.

  16. Independent contrasts and PGLS regression estimators are equivalent.

    Science.gov (United States)

    Blomberg, Simon P; Lefevre, James G; Wells, Jessie A; Waterhouse, Mary

    2012-05-01

    We prove that the slope parameter of the ordinary least squares regression of phylogenetically independent contrasts (PICs) conducted through the origin is identical to the slope parameter of the method of generalized least squares (GLSs) regression under a Brownian motion model of evolution. This equivalence has several implications: 1. Understanding the structure of the linear model for GLS regression provides insight into when and why phylogeny is important in comparative studies. 2. The limitations of the PIC regression analysis are the same as the limitations of the GLS model. In particular, phylogenetic covariance applies only to the response variable in the regression and the explanatory variable should be regarded as fixed. Calculation of PICs for explanatory variables should be treated as a mathematical idiosyncrasy of the PIC regression algorithm. 3. Since the GLS estimator is the best linear unbiased estimator (BLUE), the slope parameter estimated using PICs is also BLUE. 4. If the slope is estimated using different branch lengths for the explanatory and response variables in the PIC algorithm, the estimator is no longer the BLUE, so this is not recommended. Finally, we discuss whether or not and how to accommodate phylogenetic covariance in regression analyses, particularly in relation to the problem of phylogenetic uncertainty. This discussion is from both frequentist and Bayesian perspectives.

  17. Optimized support vector regression for drilling rate of penetration estimation

    Science.gov (United States)

    Bodaghi, Asadollah; Ansari, Hamid Reza; Gholami, Mahsa

    2015-12-01

    In the petroleum industry, drilling optimization involves the selection of operating conditions for achieving the desired depth with the minimum expenditure while requirements of personal safety, environment protection, adequate information of penetrated formations and productivity are fulfilled. Since drilling optimization is highly dependent on the rate of penetration (ROP), estimation of this parameter is of great importance during well planning. In this research, a novel approach called `optimized support vector regression' is employed for making a formulation between input variables and ROP. Algorithms used for optimizing the support vector regression are the genetic algorithm (GA) and the cuckoo search algorithm (CS). Optimization implementation improved the support vector regression performance by virtue of selecting proper values for its parameters. In order to evaluate the ability of optimization algorithms in enhancing SVR performance, their results were compared to the hybrid of pattern search and grid search (HPG) which is conventionally employed for optimizing SVR. The results demonstrated that the CS algorithm achieved further improvement on prediction accuracy of SVR compared to the GA and HPG as well. Moreover, the predictive model derived from back propagation neural network (BPNN), which is the traditional approach for estimating ROP, is selected for comparisons with CSSVR. The comparative results revealed the superiority of CSSVR. This study inferred that CSSVR is a viable option for precise estimation of ROP.

  18. Random forest variable selection in spatial malaria transmission modelling in Mpumalanga Province, South Africa

    Directory of Open Access Journals (Sweden)

    Thandi Kapwata

    2016-11-01

    Full Text Available Malaria is an environmentally driven disease. In order to quantify the spatial variability of malaria transmission, it is imperative to understand the interactions between environmental variables and malaria epidemiology at a micro-geographic level using a novel statistical approach. The random forest (RF statistical learning method, a relatively new variable-importance ranking method, measures the variable importance of potentially influential parameters through the percent increase of the mean squared error. As this value increases, so does the relative importance of the associated variable. The principal aim of this study was to create predictive malaria maps generated using the selected variables based on the RF algorithm in the Ehlanzeni District of Mpumalanga Province, South Africa. From the seven environmental variables used [temperature, lag temperature, rainfall, lag rainfall, humidity, altitude, and the normalized difference vegetation index (NDVI], altitude was identified as the most influential predictor variable due its high selection frequency. It was selected as the top predictor for 4 out of 12 months of the year, followed by NDVI, temperature and lag rainfall, which were each selected twice. The combination of climatic variables that produced the highest prediction accuracy was altitude, NDVI, and temperature. This suggests that these three variables have high predictive capabilities in relation to malaria transmission. Furthermore, it is anticipated that the predictive maps generated from predictions made by the RF algorithm could be used to monitor the progression of malaria and assist in intervention and prevention efforts with respect to malaria.

  19. A consensus successive projections algorithm--multiple linear regression method for analyzing near infrared spectra.

    Science.gov (United States)

    Liu, Ke; Chen, Xiaojing; Li, Limin; Chen, Huiling; Ruan, Xiukai; Liu, Wenbin

    2015-02-09

    The successive projections algorithm (SPA) is widely used to select variables for multiple linear regression (MLR) modeling. However, SPA used only once may not obtain all the useful information of the full spectra, because the number of selected variables cannot exceed the number of calibration samples in the SPA algorithm. Therefore, the SPA-MLR method risks the loss of useful information. To make a full use of the useful information in the spectra, a new method named "consensus SPA-MLR" (C-SPA-MLR) is proposed herein. This method is the combination of consensus strategy and SPA-MLR method. In the C-SPA-MLR method, SPA-MLR is used to construct member models with different subsets of variables, which are selected from the remaining variables iteratively. A consensus prediction is obtained by combining the predictions of the member models. The proposed method is evaluated by analyzing the near infrared (NIR) spectra of corn and diesel. The results of C-SPA-MLR method showed a better prediction performance compared with the SPA-MLR and full-spectra PLS methods. Moreover, these results could serve as a reference for combination the consensus strategy and other variable selection methods when analyzing NIR spectra and other spectroscopic techniques. Copyright © 2014 Elsevier B.V. All rights reserved.

  20. Statistical modelling for precision agriculture: A case study in optimal environmental schedules for Agaricus Bisporus production via variable domain functional regression

    Science.gov (United States)

    Panayi, Efstathios; Kyriakides, George

    2017-01-01

    Quantifying the effects of environmental factors over the duration of the growing process on Agaricus Bisporus (button mushroom) yields has been difficult, as common functional data analysis approaches require fixed length functional data. The data available from commercial growers, however, is of variable duration, due to commercial considerations. We employ a recently proposed regression technique termed Variable-Domain Functional Regression in order to be able to accommodate these irregular-length datasets. In this way, we are able to quantify the contribution of covariates such as temperature, humidity and water spraying volumes across the growing process, and for different lengths of growing processes. Our results indicate that optimal oxygen and temperature levels vary across the growing cycle and we propose environmental schedules for these covariates to optimise overall yields. PMID:28961254

  1. Multinomial logistic regression modelling of obesity and overweight among primary school students in a rural area of Negeri Sembilan

    Energy Technology Data Exchange (ETDEWEB)

    Ghazali, Amirul Syafiq Mohd; Ali, Zalila; Noor, Norlida Mohd; Baharum, Adam [Pusat Pengajian Sains Matematik, Universiti Sains Malaysia, 11800 USM, Pulau Pinang, Malaysia amirul@unisel.edu.my, zalila@cs.usm.my, norlida@usm.my, adam@usm.my (Malaysia)

    2015-10-22

    Multinomial logistic regression is widely used to model the outcomes of a polytomous response variable, a categorical dependent variable with more than two categories. The model assumes that the conditional mean of the dependent categorical variables is the logistic function of an affine combination of predictor variables. Its procedure gives a number of logistic regression models that make specific comparisons of the response categories. When there are q categories of the response variable, the model consists of q-1 logit equations which are fitted simultaneously. The model is validated by variable selection procedures, tests of regression coefficients, a significant test of the overall model, goodness-of-fit measures, and validation of predicted probabilities using odds ratio. This study used the multinomial logistic regression model to investigate obesity and overweight among primary school students in a rural area on the basis of their demographic profiles, lifestyles and on the diet and food intake. The results indicated that obesity and overweight of students are related to gender, religion, sleep duration, time spent on electronic games, breakfast intake in a week, with whom meals are taken, protein intake, and also, the interaction between breakfast intake in a week with sleep duration, and the interaction between gender and protein intake.

  2. Multinomial logistic regression modelling of obesity and overweight among primary school students in a rural area of Negeri Sembilan

    International Nuclear Information System (INIS)

    Ghazali, Amirul Syafiq Mohd; Ali, Zalila; Noor, Norlida Mohd; Baharum, Adam

    2015-01-01

    Multinomial logistic regression is widely used to model the outcomes of a polytomous response variable, a categorical dependent variable with more than two categories. The model assumes that the conditional mean of the dependent categorical variables is the logistic function of an affine combination of predictor variables. Its procedure gives a number of logistic regression models that make specific comparisons of the response categories. When there are q categories of the response variable, the model consists of q-1 logit equations which are fitted simultaneously. The model is validated by variable selection procedures, tests of regression coefficients, a significant test of the overall model, goodness-of-fit measures, and validation of predicted probabilities using odds ratio. This study used the multinomial logistic regression model to investigate obesity and overweight among primary school students in a rural area on the basis of their demographic profiles, lifestyles and on the diet and food intake. The results indicated that obesity and overweight of students are related to gender, religion, sleep duration, time spent on electronic games, breakfast intake in a week, with whom meals are taken, protein intake, and also, the interaction between breakfast intake in a week with sleep duration, and the interaction between gender and protein intake

  3. Biostatistics Series Module 6: Correlation and Linear Regression.

    Science.gov (United States)

    Hazra, Avijit; Gogtay, Nithya

    2016-01-01

    Correlation and linear regression are the most commonly used techniques for quantifying the association between two numeric variables. Correlation quantifies the strength of the linear relationship between paired variables, expressing this as a correlation coefficient. If both variables x and y are normally distributed, we calculate Pearson's correlation coefficient ( r ). If normality assumption is not met for one or both variables in a correlation analysis, a rank correlation coefficient, such as Spearman's rho (ρ) may be calculated. A hypothesis test of correlation tests whether the linear relationship between the two variables holds in the underlying population, in which case it returns a P correlation coefficient can also be calculated for an idea of the correlation in the population. The value r 2 denotes the proportion of the variability of the dependent variable y that can be attributed to its linear relation with the independent variable x and is called the coefficient of determination. Linear regression is a technique that attempts to link two correlated variables x and y in the form of a mathematical equation ( y = a + bx ), such that given the value of one variable the other may be predicted. In general, the method of least squares is applied to obtain the equation of the regression line. Correlation and linear regression analysis are based on certain assumptions pertaining to the data sets. If these assumptions are not met, misleading conclusions may be drawn. The first assumption is that of linear relationship between the two variables. A scatter plot is essential before embarking on any correlation-regression analysis to show that this is indeed the case. Outliers or clustering within data sets can distort the correlation coefficient value. Finally, it is vital to remember that though strong correlation can be a pointer toward causation, the two are not synonymous.

  4. Land-use regression with long-term satellite-based greenness index and culture-specific sources to model PM2.5 spatial-temporal variability.

    Science.gov (United States)

    Wu, Chih-Da; Chen, Yu-Cheng; Pan, Wen-Chi; Zeng, Yu-Ting; Chen, Mu-Jean; Guo, Yue Leon; Lung, Shih-Chun Candice

    2017-05-01

    This study utilized a long-term satellite-based vegetation index, and considered culture-specific emission sources (temples and Chinese restaurants) with Land-use Regression (LUR) modelling to estimate the spatial-temporal variability of PM 2.5 using data from Taipei metropolis, which exhibits typical Asian city characteristics. Annual average PM 2.5 concentrations from 2006 to 2012 of 17 air quality monitoring stations established by Environmental Protection Administration of Taiwan were used for model development. PM 2.5 measurements from 2013 were used for external data verification. Monthly Normalized Difference Vegetation Index (NDVI) images coupled with buffer analysis were used to assess the spatial-temporal variations of greenness surrounding the monitoring sites. The distribution of temples and Chinese restaurants were included to represent the emission contributions from incense and joss money burning, and gas cooking, respectively. Spearman correlation coefficient and stepwise regression were used for LUR model development, and 10-fold cross-validation and external data verification were applied to verify the model reliability. The results showed a strongly negative correlation (r: -0.71 to -0.77) between NDVI and PM 2.5 while temples (r: 0.52 to 0.66) and Chinese restaurants (r: 0.31 to 0.44) were positively correlated to PM 2.5 concentrations. With the adjusted model R 2 of 0.89, a cross-validated adj-R 2 of 0.90, and external validated R 2 of 0.83, the high explanatory power of the resultant model was confirmed. Moreover, the averaged NDVI within a 1750 m circular buffer (p < 0.01), the number of Chinese restaurants within a 1750 m buffer (p < 0.01), and the number of temples within a 750 m buffer (p = 0.06) were selected as important predictors during the stepwise selection procedures. According to the partial R 2 , NDVI explained 66% of PM 2.5 variation and was the dominant variable in the developed model. We suggest future studies

  5. Few crystal balls are crystal clear : eyeballing regression

    International Nuclear Information System (INIS)

    Wittebrood, R.T.

    1998-01-01

    The theory of regression and statistical analysis as it applies to reservoir analysis was discussed. It was argued that regression lines are not always the final truth. It was suggested that regression lines and eyeballed lines are often equally accurate. The many conditions that must be fulfilled to calculate a proper regression were discussed. Mentioned among these conditions were the distribution of the data, hidden variables, knowledge of how the data was obtained, the need for causal correlation of the variables, and knowledge of the manner in which the regression results are going to be used. 1 tab., 13 figs

  6. A Time-Series Water Level Forecasting Model Based on Imputation and Variable Selection Method

    Directory of Open Access Journals (Sweden)

    Jun-He Yang

    2017-01-01

    Full Text Available Reservoirs are important for households and impact the national economy. This paper proposed a time-series forecasting model based on estimating a missing value followed by variable selection to forecast the reservoir’s water level. This study collected data from the Taiwan Shimen Reservoir as well as daily atmospheric data from 2008 to 2015. The two datasets are concatenated into an integrated dataset based on ordering of the data as a research dataset. The proposed time-series forecasting model summarily has three foci. First, this study uses five imputation methods to directly delete the missing value. Second, we identified the key variable via factor analysis and then deleted the unimportant variables sequentially via the variable selection method. Finally, the proposed model uses a Random Forest to build the forecasting model of the reservoir’s water level. This was done to compare with the listing method under the forecasting error. These experimental results indicate that the Random Forest forecasting model when applied to variable selection with full variables has better forecasting performance than the listing model. In addition, this experiment shows that the proposed variable selection can help determine five forecast methods used here to improve the forecasting capability.

  7. RAWS II: A MULTIPLE REGRESSION ANALYSIS PROGRAM,

    Science.gov (United States)

    This memorandum gives instructions for the use and operation of a revised version of RAWS, a multiple regression analysis program. The program...of preprocessed data, the directed retention of variable, listing of the matrix of the normal equations and its inverse, and the bypassing of the regression analysis to provide the input variable statistics only. (Author)

  8. Moderation analysis using a two-level regression model.

    Science.gov (United States)

    Yuan, Ke-Hai; Cheng, Ying; Maxwell, Scott

    2014-10-01

    Moderation analysis is widely used in social and behavioral research. The most commonly used model for moderation analysis is moderated multiple regression (MMR) in which the explanatory variables of the regression model include product terms, and the model is typically estimated by least squares (LS). This paper argues for a two-level regression model in which the regression coefficients of a criterion variable on predictors are further regressed on moderator variables. An algorithm for estimating the parameters of the two-level model by normal-distribution-based maximum likelihood (NML) is developed. Formulas for the standard errors (SEs) of the parameter estimates are provided and studied. Results indicate that, when heteroscedasticity exists, NML with the two-level model gives more efficient and more accurate parameter estimates than the LS analysis of the MMR model. When error variances are homoscedastic, NML with the two-level model leads to essentially the same results as LS with the MMR model. Most importantly, the two-level regression model permits estimating the percentage of variance of each regression coefficient that is due to moderator variables. When applied to data from General Social Surveys 1991, NML with the two-level model identified a significant moderation effect of race on the regression of job prestige on years of education while LS with the MMR model did not. An R package is also developed and documented to facilitate the application of the two-level model.

  9. Assessing the accuracy and stability of variable selection methods for random forest modeling in ecology.

    Science.gov (United States)

    Fox, Eric W; Hill, Ryan A; Leibowitz, Scott G; Olsen, Anthony R; Thornbrugh, Darren J; Weber, Marc H

    2017-07-01

    Random forest (RF) modeling has emerged as an important statistical learning method in ecology due to its exceptional predictive performance. However, for large and complex ecological data sets, there is limited guidance on variable selection methods for RF modeling. Typically, either a preselected set of predictor variables are used or stepwise procedures are employed which iteratively remove variables according to their importance measures. This paper investigates the application of variable selection methods to RF models for predicting probable biological stream condition. Our motivating data set consists of the good/poor condition of n = 1365 stream survey sites from the 2008/2009 National Rivers and Stream Assessment, and a large set (p = 212) of landscape features from the StreamCat data set as potential predictors. We compare two types of RF models: a full variable set model with all 212 predictors and a reduced variable set model selected using a backward elimination approach. We assess model accuracy using RF's internal out-of-bag estimate, and a cross-validation procedure with validation folds external to the variable selection process. We also assess the stability of the spatial predictions generated by the RF models to changes in the number of predictors and argue that model selection needs to consider both accuracy and stability. The results suggest that RF modeling is robust to the inclusion of many variables of moderate to low importance. We found no substantial improvement in cross-validated accuracy as a result of variable reduction. Moreover, the backward elimination procedure tended to select too few variables and exhibited numerous issues such as upwardly biased out-of-bag accuracy estimates and instabilities in the spatial predictions. We use simulations to further support and generalize results from the analysis of real data. A main purpose of this work is to elucidate issues of model selection bias and instability to ecologists interested in

  10. Yet another look at MIDAS regression

    NARCIS (Netherlands)

    Ph.H.B.F. Franses (Philip Hans)

    2016-01-01

    textabstractA MIDAS regression involves a dependent variable observed at a low frequency and independent variables observed at a higher frequency. This paper relates a true high frequency data generating process, where also the dependent variable is observed (hypothetically) at the high frequency,

  11. Predictors of Placement Stability at the State Level: The Use of Logistic Regression to Inform Practice

    Science.gov (United States)

    Courtney, Jon R.; Prophet, Retta

    2011-01-01

    Placement instability is often associated with a number of negative outcomes for children. To gain state level contextual knowledge of factors associated with placement stability/instability, logistic regression was applied to selected variables from the New Mexico Adoption and Foster Care Administrative Reporting System dataset. Predictors…

  12. Selecting groups of covariates in the elastic net

    DEFF Research Database (Denmark)

    Clemmensen, Line Katrine Harder

    This paper introduces a novel method to select groups of variables in sparse regression and classication settings. The groups are formed based on the correlations between covariates and ensure that for example spatial or spectral relations are preserved without explicitly coding for these....... The preservation of relations gives increased interpretability. The method is based on the elastic net and adaptively selects highly correlated groups of variables and does therefore not waste time in grouping irrelevant variables for the problem at hand. The method is illustrated on a simulated data set...

  13. A regression modeling approach for studying carbonate system variability in the northern Gulf of Alaska

    Science.gov (United States)

    Evans, Wiley; Mathis, Jeremy T.; Winsor, Peter; Statscewich, Hank; Whitledge, Terry E.

    2013-01-01

    northern Gulf of Alaska (GOA) shelf experiences carbonate system variability on seasonal and annual time scales, but little information exists to resolve higher frequency variability in this region. To resolve this variability using platforms-of-opportunity, we present multiple linear regression (MLR) models constructed from hydrographic data collected along the Northeast Pacific Global Ocean Ecosystems Dynamics (GLOBEC) Seward Line. The empirical algorithms predict dissolved inorganic carbon (DIC) and total alkalinity (TA) using observations of nitrate (NO3-), temperature, salinity and pressure from the surface to 500 m, with R2s > 0.97 and RMSE values of 11 µmol kg-1 for DIC and 9 µmol kg-1 for TA. We applied these relationships to high-resolution NO3- data sets collected during a novel 20 h glider flight and a GLOBEC mesoscale SeaSoar survey. Results from the glider flight demonstrated time/space along-isopycnal variability of aragonite saturations (Ωarag) associated with a dicothermal layer (a cold near-surface layer found in high latitude oceans) that rivaled changes seen vertically through the thermocline. The SeaSoar survey captured the uplift to aragonite saturation horizon (depth where Ωarag = 1) shoaled to a previously unseen depth in the northern GOA. This work is similar to recent studies aimed at predicting the carbonate system in continental margin settings, albeit demonstrates that a NO3--based approach can be applied to high-latitude data collected from platforms capable of high-frequency measurements.

  14. Molecular Classification Substitutes for the Prognostic Variables Stage, Age, and MYCN Status in Neuroblastoma Risk Assessment

    Directory of Open Access Journals (Sweden)

    Carolina Rosswog

    2017-12-01

    Full Text Available BACKGROUND: Current risk stratification systems for neuroblastoma patients consider clinical, histopathological, and genetic variables, and additional prognostic markers have been proposed in recent years. We here sought to select highly informative covariates in a multistep strategy based on consecutive Cox regression models, resulting in a risk score that integrates hazard ratios of prognostic variables. METHODS: A cohort of 695 neuroblastoma patients was divided into a discovery set (n = 75 for multigene predictor generation, a training set (n = 411 for risk score development, and a validation set (n = 209. Relevant prognostic variables were identified by stepwise multivariable L1-penalized least absolute shrinkage and selection operator (LASSO Cox regression, followed by backward selection in multivariable Cox regression, and then integrated into a novel risk score. RESULTS: The variables stage, age, MYCN status, and two multigene predictors, NB-th24 and NB-th44, were selected as independent prognostic markers by LASSO Cox regression analysis. Following backward selection, only the multigene predictors were retained in the final model. Integration of these classifiers in a risk scoring system distinguished three patient subgroups that differed substantially in their outcome. The scoring system discriminated patients with diverging outcome in the validation cohort (5-year event-free survival, 84.9 ± 3.4 vs 63.6 ± 14.5 vs 31.0 ± 5.4; P < .001, and its prognostic value was validated by multivariable analysis. CONCLUSION: We here propose a translational strategy for developing risk assessment systems based on hazard ratios of relevant prognostic variables. Our final neuroblastoma risk score comprised two multigene predictors only, supporting the notion that molecular properties of the tumor cells strongly impact clinical courses of neuroblastoma patients.

  15. Molecular Classification Substitutes for the Prognostic Variables Stage, Age, and MYCN Status in Neuroblastoma Risk Assessment.

    Science.gov (United States)

    Rosswog, Carolina; Schmidt, Rene; Oberthuer, André; Juraeva, Dilafruz; Brors, Benedikt; Engesser, Anne; Kahlert, Yvonne; Volland, Ruth; Bartenhagen, Christoph; Simon, Thorsten; Berthold, Frank; Hero, Barbara; Faldum, Andreas; Fischer, Matthias

    2017-12-01

    Current risk stratification systems for neuroblastoma patients consider clinical, histopathological, and genetic variables, and additional prognostic markers have been proposed in recent years. We here sought to select highly informative covariates in a multistep strategy based on consecutive Cox regression models, resulting in a risk score that integrates hazard ratios of prognostic variables. A cohort of 695 neuroblastoma patients was divided into a discovery set (n=75) for multigene predictor generation, a training set (n=411) for risk score development, and a validation set (n=209). Relevant prognostic variables were identified by stepwise multivariable L1-penalized least absolute shrinkage and selection operator (LASSO) Cox regression, followed by backward selection in multivariable Cox regression, and then integrated into a novel risk score. The variables stage, age, MYCN status, and two multigene predictors, NB-th24 and NB-th44, were selected as independent prognostic markers by LASSO Cox regression analysis. Following backward selection, only the multigene predictors were retained in the final model. Integration of these classifiers in a risk scoring system distinguished three patient subgroups that differed substantially in their outcome. The scoring system discriminated patients with diverging outcome in the validation cohort (5-year event-free survival, 84.9±3.4 vs 63.6±14.5 vs 31.0±5.4; P<.001), and its prognostic value was validated by multivariable analysis. We here propose a translational strategy for developing risk assessment systems based on hazard ratios of relevant prognostic variables. Our final neuroblastoma risk score comprised two multigene predictors only, supporting the notion that molecular properties of the tumor cells strongly impact clinical courses of neuroblastoma patients. Copyright © 2017 The Authors. Published by Elsevier Inc. All rights reserved.

  16. Parameters Estimation of Geographically Weighted Ordinal Logistic Regression (GWOLR) Model

    Science.gov (United States)

    Zuhdi, Shaifudin; Retno Sari Saputro, Dewi; Widyaningsih, Purnami

    2017-06-01

    A regression model is the representation of relationship between independent variable and dependent variable. The dependent variable has categories used in the logistic regression model to calculate odds on. The logistic regression model for dependent variable has levels in the logistics regression model is ordinal. GWOLR model is an ordinal logistic regression model influenced the geographical location of the observation site. Parameters estimation in the model needed to determine the value of a population based on sample. The purpose of this research is to parameters estimation of GWOLR model using R software. Parameter estimation uses the data amount of dengue fever patients in Semarang City. Observation units used are 144 villages in Semarang City. The results of research get GWOLR model locally for each village and to know probability of number dengue fever patient categories.

  17. Variability-based active galactic nucleus selection using image subtraction in the SDSS and LSST era

    Energy Technology Data Exchange (ETDEWEB)

    Choi, Yumi; Gibson, Robert R.; Becker, Andrew C.; Ivezić, Željko; Connolly, Andrew J.; Ruan, John J.; Anderson, Scott F. [Department of Astronomy, University of Washington, Box 351580, Seattle, WA 98195 (United States); MacLeod, Chelsea L., E-mail: ymchoi@astro.washington.edu [Physics Department, U.S. Naval Academy, 572 Holloway Road, Annapolis, MD 21402 (United States)

    2014-02-10

    With upcoming all-sky surveys such as LSST poised to generate a deep digital movie of the optical sky, variability-based active galactic nucleus (AGN) selection will enable the construction of highly complete catalogs with minimum contamination. In this study, we generate g-band difference images and construct light curves (LCs) for QSO/AGN candidates listed in Sloan Digital Sky Survey Stripe 82 public catalogs compiled from different methods, including spectroscopy, optical colors, variability, and X-ray detection. Image differencing excels at identifying variable sources embedded in complex or blended emission regions such as Type II AGNs and other low-luminosity AGNs that may be omitted from traditional photometric or spectroscopic catalogs. To separate QSOs/AGNs from other sources using our difference image LCs, we explore several LC statistics and parameterize optical variability by the characteristic damping timescale (τ) and variability amplitude. By virtue of distinguishable variability parameters of AGNs, we are able to select them with high completeness of 93.4% and efficiency (i.e., purity) of 71.3%. Based on optical variability, we also select highly variable blazar candidates, whose infrared colors are consistent with known blazars. One-third of them are also radio detected. With the X-ray selected AGN candidates, we probe the optical variability of X-ray detected optically extended sources using their difference image LCs for the first time. A combination of optical variability and X-ray detection enables us to select various types of host-dominated AGNs. Contrary to the AGN unification model prediction, two Type II AGN candidates (out of six) show detectable variability on long-term timescales like typical Type I AGNs. This study will provide a baseline for future optical variability studies of extended sources.

  18. Nonparametric instrumental regression with non-convex constraints

    International Nuclear Information System (INIS)

    Grasmair, M; Scherzer, O; Vanhems, A

    2013-01-01

    This paper considers the nonparametric regression model with an additive error that is dependent on the explanatory variables. As is common in empirical studies in epidemiology and economics, it also supposes that valid instrumental variables are observed. A classical example in microeconomics considers the consumer demand function as a function of the price of goods and the income, both variables often considered as endogenous. In this framework, the economic theory also imposes shape restrictions on the demand function, such as integrability conditions. Motivated by this illustration in microeconomics, we study an estimator of a nonparametric constrained regression function using instrumental variables by means of Tikhonov regularization. We derive rates of convergence for the regularized model both in a deterministic and stochastic setting under the assumption that the true regression function satisfies a projected source condition including, because of the non-convexity of the imposed constraints, an additional smallness condition. (paper)

  19. Nonparametric instrumental regression with non-convex constraints

    Science.gov (United States)

    Grasmair, M.; Scherzer, O.; Vanhems, A.

    2013-03-01

    This paper considers the nonparametric regression model with an additive error that is dependent on the explanatory variables. As is common in empirical studies in epidemiology and economics, it also supposes that valid instrumental variables are observed. A classical example in microeconomics considers the consumer demand function as a function of the price of goods and the income, both variables often considered as endogenous. In this framework, the economic theory also imposes shape restrictions on the demand function, such as integrability conditions. Motivated by this illustration in microeconomics, we study an estimator of a nonparametric constrained regression function using instrumental variables by means of Tikhonov regularization. We derive rates of convergence for the regularized model both in a deterministic and stochastic setting under the assumption that the true regression function satisfies a projected source condition including, because of the non-convexity of the imposed constraints, an additional smallness condition.

  20. Principal component regression for crop yield estimation

    CERN Document Server

    Suryanarayana, T M V

    2016-01-01

    This book highlights the estimation of crop yield in Central Gujarat, especially with regard to the development of Multiple Regression Models and Principal Component Regression (PCR) models using climatological parameters as independent variables and crop yield as a dependent variable. It subsequently compares the multiple linear regression (MLR) and PCR results, and discusses the significance of PCR for crop yield estimation. In this context, the book also covers Principal Component Analysis (PCA), a statistical procedure used to reduce a number of correlated variables into a smaller number of uncorrelated variables called principal components (PC). This book will be helpful to the students and researchers, starting their works on climate and agriculture, mainly focussing on estimation models. The flow of chapters takes the readers in a smooth path, in understanding climate and weather and impact of climate change, and gradually proceeds towards downscaling techniques and then finally towards development of ...

  1. Regression Analysis by Example. 5th Edition

    Science.gov (United States)

    Chatterjee, Samprit; Hadi, Ali S.

    2012-01-01

    Regression analysis is a conceptually simple method for investigating relationships among variables. Carrying out a successful application of regression analysis, however, requires a balance of theoretical results, empirical rules, and subjective judgment. "Regression Analysis by Example, Fifth Edition" has been expanded and thoroughly…

  2. Logistic Regression: Concept and Application

    Science.gov (United States)

    Cokluk, Omay

    2010-01-01

    The main focus of logistic regression analysis is classification of individuals in different groups. The aim of the present study is to explain basic concepts and processes of binary logistic regression analysis intended to determine the combination of independent variables which best explain the membership in certain groups called dichotomous…

  3. BOX-COX REGRESSION METHOD IN TIME SCALING

    Directory of Open Access Journals (Sweden)

    ATİLLA GÖKTAŞ

    2013-06-01

    Full Text Available Box-Cox regression method with λj, for j = 1, 2, ..., k, power transformation can be used when dependent variable and error term of the linear regression model do not satisfy the continuity and normality assumptions. The situation obtaining the smallest mean square error  when optimum power λj, transformation for j = 1, 2, ..., k, of Y has been discussed. Box-Cox regression method is especially appropriate to adjust existence skewness or heteroscedasticity of error terms for a nonlinear functional relationship between dependent and explanatory variables. In this study, the advantage and disadvantage use of Box-Cox regression method have been discussed in differentiation and differantial analysis of time scale concept.

  4. Discussion on Regression Methods Based on Ensemble Learning and Applicability Domains of Linear Submodels.

    Science.gov (United States)

    Kaneko, Hiromasa

    2018-02-26

    To develop a new ensemble learning method and construct highly predictive regression models in chemoinformatics and chemometrics, applicability domains (ADs) are introduced into the ensemble learning process of prediction. When estimating values of an objective variable using subregression models, only the submodels with ADs that cover a query sample, i.e., the sample is inside the model's AD, are used. By constructing submodels and changing a list of selected explanatory variables, the union of the submodels' ADs, which defines the overall AD, becomes large, and the prediction performance is enhanced for diverse compounds. By analyzing a quantitative structure-activity relationship data set and a quantitative structure-property relationship data set, it is confirmed that the ADs can be enlarged and the estimation performance of regression models is improved compared with traditional methods.

  5. Estimating HIES Data through Ratio and Regression Methods for Different Sampling Designs

    Directory of Open Access Journals (Sweden)

    Faqir Muhammad

    2007-01-01

    Full Text Available In this study, comparison has been made for different sampling designs, using the HIES data of North West Frontier Province (NWFP for 2001-02 and 1998-99 collected from the Federal Bureau of Statistics, Statistical Division, Government of Pakistan, Islamabad. The performance of the estimators has also been considered using bootstrap and Jacknife. A two-stage stratified random sample design is adopted by HIES. In the first stage, enumeration blocks and villages are treated as the first stage Primary Sampling Units (PSU. The sample PSU’s are selected with probability proportional to size. Secondary Sampling Units (SSU i.e., households are selected by systematic sampling with a random start. They have used a single study variable. We have compared the HIES technique with some other designs, which are: Stratified Simple Random Sampling. Stratified Systematic Sampling. Stratified Ranked Set Sampling. Stratified Two Phase Sampling. Ratio and Regression methods were applied with two study variables, which are: Income (y and Household sizes (x. Jacknife and Bootstrap are used for variance replication. Simple Random Sampling with sample size (462 to 561 gave moderate variances both by Jacknife and Bootstrap. By applying Systematic Sampling, we received moderate variance with sample size (467. In Jacknife with Systematic Sampling, we obtained variance of regression estimator greater than that of ratio estimator for a sample size (467 to 631. At a sample size (952 variance of ratio estimator gets greater than that of regression estimator. The most efficient design comes out to be Ranked set sampling compared with other designs. The Ranked set sampling with jackknife and bootstrap, gives minimum variance even with the smallest sample size (467. Two Phase sampling gave poor performance. Multi-stage sampling applied by HIES gave large variances especially if used with a single study variable.

  6. Principal component regression analysis with SPSS.

    Science.gov (United States)

    Liu, R X; Kuang, J; Gong, Q; Hou, X L

    2003-06-01

    The paper introduces all indices of multicollinearity diagnoses, the basic principle of principal component regression and determination of 'best' equation method. The paper uses an example to describe how to do principal component regression analysis with SPSS 10.0: including all calculating processes of the principal component regression and all operations of linear regression, factor analysis, descriptives, compute variable and bivariate correlations procedures in SPSS 10.0. The principal component regression analysis can be used to overcome disturbance of the multicollinearity. The simplified, speeded up and accurate statistical effect is reached through the principal component regression analysis with SPSS.

  7. Using Logistic Regression To Predict the Probability of Debris Flows Occurring in Areas Recently Burned By Wildland Fires

    Science.gov (United States)

    Rupert, Michael G.; Cannon, Susan H.; Gartner, Joseph E.

    2003-01-01

    Logistic regression was used to predict the probability of debris flows occurring in areas recently burned by wildland fires. Multiple logistic regression is conceptually similar to multiple linear regression because statistical relations between one dependent variable and several independent variables are evaluated. In logistic regression, however, the dependent variable is transformed to a binary variable (debris flow did or did not occur), and the actual probability of the debris flow occurring is statistically modeled. Data from 399 basins located within 15 wildland fires that burned during 2000-2002 in Colorado, Idaho, Montana, and New Mexico were evaluated. More than 35 independent variables describing the burn severity, geology, land surface gradient, rainfall, and soil properties were evaluated. The models were developed as follows: (1) Basins that did and did not produce debris flows were delineated from National Elevation Data using a Geographic Information System (GIS). (2) Data describing the burn severity, geology, land surface gradient, rainfall, and soil properties were determined for each basin. These data were then downloaded to a statistics software package for analysis using logistic regression. (3) Relations between the occurrence/non-occurrence of debris flows and burn severity, geology, land surface gradient, rainfall, and soil properties were evaluated and several preliminary multivariate logistic regression models were constructed. All possible combinations of independent variables were evaluated to determine which combination produced the most effective model. The multivariate model that best predicted the occurrence of debris flows was selected. (4) The multivariate logistic regression model was entered into a GIS, and a map showing the probability of debris flows was constructed. The most effective model incorporates the percentage of each basin with slope greater than 30 percent, percentage of land burned at medium and high burn severity

  8. Determinants of Smartphone Selection: An Application of the University Students

    Directory of Open Access Journals (Sweden)

    Halim TATLI

    2015-12-01

    Full Text Available In this study, we aimed to identify the factors that impact on smartphone selection of university students. In this context, the data is obtained from a survey which is conducted to students that are studying in Bingöl University. This questionnaire was administered to 400 students in the November-October 2014. Student’s smartphone selection response variable, the logarithm of age, the logarithm of income and logarithm of the scores of the students' perspective on smart phone is taken as an explanatory variable. In the analysis were used logistic regression. The estimated results of logistic regression analysis; logarithm of the scores of the students' perspective on smart phone and the the logarithm of income was be found to increase the likelihood of smartphone selection in a meaningful way. Between the logarithm of age and smartphone selection was not found to be significant relationship. The results of the study, showed that the major determinants of smartphone selection monthly income and students' perspective on smartphones.

  9. Poisson Mixture Regression Models for Heart Disease Prediction.

    Science.gov (United States)

    Mufudza, Chipo; Erol, Hamza

    2016-01-01

    Early heart disease control can be achieved by high disease prediction and diagnosis efficiency. This paper focuses on the use of model based clustering techniques to predict and diagnose heart disease via Poisson mixture regression models. Analysis and application of Poisson mixture regression models is here addressed under two different classes: standard and concomitant variable mixture regression models. Results show that a two-component concomitant variable Poisson mixture regression model predicts heart disease better than both the standard Poisson mixture regression model and the ordinary general linear Poisson regression model due to its low Bayesian Information Criteria value. Furthermore, a Zero Inflated Poisson Mixture Regression model turned out to be the best model for heart prediction over all models as it both clusters individuals into high or low risk category and predicts rate to heart disease componentwise given clusters available. It is deduced that heart disease prediction can be effectively done by identifying the major risks componentwise using Poisson mixture regression model.

  10. Poisson Mixture Regression Models for Heart Disease Prediction

    Science.gov (United States)

    Erol, Hamza

    2016-01-01

    Early heart disease control can be achieved by high disease prediction and diagnosis efficiency. This paper focuses on the use of model based clustering techniques to predict and diagnose heart disease via Poisson mixture regression models. Analysis and application of Poisson mixture regression models is here addressed under two different classes: standard and concomitant variable mixture regression models. Results show that a two-component concomitant variable Poisson mixture regression model predicts heart disease better than both the standard Poisson mixture regression model and the ordinary general linear Poisson regression model due to its low Bayesian Information Criteria value. Furthermore, a Zero Inflated Poisson Mixture Regression model turned out to be the best model for heart prediction over all models as it both clusters individuals into high or low risk category and predicts rate to heart disease componentwise given clusters available. It is deduced that heart disease prediction can be effectively done by identifying the major risks componentwise using Poisson mixture regression model. PMID:27999611

  11. A computational approach to compare regression modelling strategies in prediction research.

    Science.gov (United States)

    Pajouheshnia, Romin; Pestman, Wiebe R; Teerenstra, Steven; Groenwold, Rolf H H

    2016-08-25

    It is often unclear which approach to fit, assess and adjust a model will yield the most accurate prediction model. We present an extension of an approach for comparing modelling strategies in linear regression to the setting of logistic regression and demonstrate its application in clinical prediction research. A framework for comparing logistic regression modelling strategies by their likelihoods was formulated using a wrapper approach. Five different strategies for modelling, including simple shrinkage methods, were compared in four empirical data sets to illustrate the concept of a priori strategy comparison. Simulations were performed in both randomly generated data and empirical data to investigate the influence of data characteristics on strategy performance. We applied the comparison framework in a case study setting. Optimal strategies were selected based on the results of a priori comparisons in a clinical data set and the performance of models built according to each strategy was assessed using the Brier score and calibration plots. The performance of modelling strategies was highly dependent on the characteristics of the development data in both linear and logistic regression settings. A priori comparisons in four empirical data sets found that no strategy consistently outperformed the others. The percentage of times that a model adjustment strategy outperformed a logistic model ranged from 3.9 to 94.9 %, depending on the strategy and data set. However, in our case study setting the a priori selection of optimal methods did not result in detectable improvement in model performance when assessed in an external data set. The performance of prediction modelling strategies is a data-dependent process and can be highly variable between data sets within the same clinical domain. A priori strategy comparison can be used to determine an optimal logistic regression modelling strategy for a given data set before selecting a final modelling approach.

  12. Protein construct storage: Bayesian variable selection and prediction with mixtures.

    Science.gov (United States)

    Clyde, M A; Parmigiani, G

    1998-07-01

    Determining optimal conditions for protein storage while maintaining a high level of protein activity is an important question in pharmaceutical research. A designed experiment based on a space-filling design was conducted to understand the effects of factors affecting protein storage and to establish optimal storage conditions. Different model-selection strategies to identify important factors may lead to very different answers about optimal conditions. Uncertainty about which factors are important, or model uncertainty, can be a critical issue in decision-making. We use Bayesian variable selection methods for linear models to identify important variables in the protein storage data, while accounting for model uncertainty. We also use the Bayesian framework to build predictions based on a large family of models, rather than an individual model, and to evaluate the probability that certain candidate storage conditions are optimal.

  13. An improved multiple linear regression and data analysis computer program package

    Science.gov (United States)

    Sidik, S. M.

    1972-01-01

    NEWRAP, an improved version of a previous multiple linear regression program called RAPIER, CREDUC, and CRSPLT, allows for a complete regression analysis including cross plots of the independent and dependent variables, correlation coefficients, regression coefficients, analysis of variance tables, t-statistics and their probability levels, rejection of independent variables, plots of residuals against the independent and dependent variables, and a canonical reduction of quadratic response functions useful in optimum seeking experimentation. A major improvement over RAPIER is that all regression calculations are done in double precision arithmetic.

  14. Nonlinear Forecasting With Many Predictors Using Kernel Ridge Regression

    DEFF Research Database (Denmark)

    Exterkate, Peter; Groenen, Patrick J.F.; Heij, Christiaan

    This paper puts forward kernel ridge regression as an approach for forecasting with many predictors that are related nonlinearly to the target variable. In kernel ridge regression, the observed predictor variables are mapped nonlinearly into a high-dimensional space, where estimation of the predi...

  15. The XRF spectrometer and the selection of analysis conditions (instrumental variables)

    International Nuclear Information System (INIS)

    Willis, J.P.

    2002-01-01

    Full text: This presentation will begin with a brief discussion of EDXRF and flat- and curved-crystal WDXRF spectrometers, contrasting the major differences between the three types. The remainder of the presentation will contain a detailed overview of the choice and settings of the many instrumental variables contained in a modern WDXRF spectrometer, and will discuss critically the choices facing the analyst in setting up a WDXRF spectrometer for different elements and applications. In particular it will discuss the choice of tube target (when a choice is possible), the kV and mA settings, tube filters, collimator masks, collimators, analyzing crystals, secondary collimators, detectors, pulse height selection, X-ray path medium (air, nitrogen, vacuum or helium), counting times for peak and background positions and their effect on counting statistics and lower limit of detection (LLD). The use of Figure of Merit (FOM) calculations to objectively choose the best combination of instrumental variables also will be discussed. This presentation will be followed by a shorter session on a subsequent day entitled - A Selection of XRF Conditions - Practical Session, where participants will be given the opportunity to discuss in groups the selection of the best instrumental variables for three very diverse applications. Copyright (2002) Australian X-ray Analytical Association Inc

  16. Regional regression equations for the estimation of selected monthly low-flow duration and frequency statistics at ungaged sites on streams in New Jersey

    Science.gov (United States)

    Watson, Kara M.; McHugh, Amy R.

    2014-01-01

    Regional regression equations were developed for estimating monthly flow-duration and monthly low-flow frequency statistics for ungaged streams in Coastal Plain and non-coastal regions of New Jersey for baseline and current land- and water-use conditions. The equations were developed to estimate 87 different streamflow statistics, which include the monthly 99-, 90-, 85-, 75-, 50-, and 25-percentile flow-durations of the minimum 1-day daily flow; the August–September 99-, 90-, and 75-percentile minimum 1-day daily flow; and the monthly 7-day, 10-year (M7D10Y) low-flow frequency. These 87 streamflow statistics were computed for 41 continuous-record streamflow-gaging stations (streamgages) with 20 or more years of record and 167 low-flow partial-record stations in New Jersey with 10 or more streamflow measurements. The regression analyses used to develop equations to estimate selected streamflow statistics were performed by testing the relation between flow-duration statistics and low-flow frequency statistics for 32 basin characteristics (physical characteristics, land use, surficial geology, and climate) at the 41 streamgages and 167 low-flow partial-record stations. The regression analyses determined drainage area, soil permeability, average April precipitation, average June precipitation, and percent storage (water bodies and wetlands) were the significant explanatory variables for estimating the selected flow-duration and low-flow frequency statistics. Streamflow estimates were computed for two land- and water-use conditions in New Jersey—land- and water-use during the baseline period of record (defined as the years a streamgage had little to no change in development and water use) and current land- and water-use conditions (1989–2008)—for each selected station using data collected through water year 2008. The baseline period of record is representative of a period when the basin was unaffected by change in development. The current period is

  17. A flexible fuzzy regression algorithm for forecasting oil consumption estimation

    International Nuclear Information System (INIS)

    Azadeh, A.; Khakestani, M.; Saberi, M.

    2009-01-01

    Oil consumption plays a vital role in socio-economic development of most countries. This study presents a flexible fuzzy regression algorithm for forecasting oil consumption based on standard economic indicators. The standard indicators are annual population, cost of crude oil import, gross domestic production (GDP) and annual oil production in the last period. The proposed algorithm uses analysis of variance (ANOVA) to select either fuzzy regression or conventional regression for future demand estimation. The significance of the proposed algorithm is three fold. First, it is flexible and identifies the best model based on the results of ANOVA and minimum absolute percentage error (MAPE), whereas previous studies consider the best fitted fuzzy regression model based on MAPE or other relative error results. Second, the proposed model may identify conventional regression as the best model for future oil consumption forecasting because of its dynamic structure, whereas previous studies assume that fuzzy regression always provide the best solutions and estimation. Third, it utilizes the most standard independent variables for the regression models. To show the applicability and superiority of the proposed flexible fuzzy regression algorithm the data for oil consumption in Canada, United States, Japan and Australia from 1990 to 2005 are used. The results show that the flexible algorithm provides accurate solution for oil consumption estimation problem. The algorithm may be used by policy makers to accurately foresee the behavior of oil consumption in various regions.

  18. Tutorial on Using Regression Models with Count Outcomes Using R

    Directory of Open Access Journals (Sweden)

    A. Alexander Beaujean

    2016-02-01

    Full Text Available Education researchers often study count variables, such as times a student reached a goal, discipline referrals, and absences. Most researchers that study these variables use typical regression methods (i.e., ordinary least-squares either with or without transforming the count variables. In either case, using typical regression for count data can produce parameter estimates that are biased, thus diminishing any inferences made from such data. As count-variable regression models are seldom taught in training programs, we present a tutorial to help educational researchers use such methods in their own research. We demonstrate analyzing and interpreting count data using Poisson, negative binomial, zero-inflated Poisson, and zero-inflated negative binomial regression models. The count regression methods are introduced through an example using the number of times students skipped class. The data for this example are freely available and the R syntax used run the example analyses are included in the Appendix.

  19. A comparison of logistic regression analysis and an artificial neural network using the BI-RADS lexicon for ultrasonography in conjunction with introbserver variability.

    Science.gov (United States)

    Kim, Sun Mi; Han, Heon; Park, Jeong Mi; Choi, Yoon Jung; Yoon, Hoi Soo; Sohn, Jung Hee; Baek, Moon Hee; Kim, Yoon Nam; Chae, Young Moon; June, Jeon Jong; Lee, Jiwon; Jeon, Yong Hwan

    2012-10-01

    To determine which Breast Imaging Reporting and Data System (BI-RADS) descriptors for ultrasound are predictors for breast cancer using logistic regression (LR) analysis in conjunction with interobserver variability between breast radiologists, and to compare the performance of artificial neural network (ANN) and LR models in differentiation of benign and malignant breast masses. Five breast radiologists retrospectively reviewed 140 breast masses and described each lesion using BI-RADS lexicon and categorized final assessments. Interobserver agreements between the observers were measured by kappa statistics. The radiologists' responses for BI-RADS were pooled. The data were divided randomly into train (n = 70) and test sets (n = 70). Using train set, optimal independent variables were determined by using LR analysis with forward stepwise selection. The LR and ANN models were constructed with the optimal independent variables and the biopsy results as dependent variable. Performances of the models and radiologists were evaluated on the test set using receiver-operating characteristic (ROC) analysis. Among BI-RADS descriptors, margin and boundary were determined as the predictors according to stepwise LR showing moderate interobserver agreement. Area under the ROC curves (AUC) for both of LR and ANN were 0.87 (95% CI, 0.77-0.94). AUCs for the five radiologists ranged 0.79-0.91. There was no significant difference in AUC values among the LR, ANN, and radiologists (p > 0.05). Margin and boundary were found as statistically significant predictors with good interobserver agreement. Use of the LR and ANN showed similar performance to that of the radiologists for differentiation of benign and malignant breast masses.

  20. Better Autologistic Regression

    Directory of Open Access Journals (Sweden)

    Mark A. Wolters

    2017-11-01

    Full Text Available Autologistic regression is an important probability model for dichotomous random variables observed along with covariate information. It has been used in various fields for analyzing binary data possessing spatial or network structure. The model can be viewed as an extension of the autologistic model (also known as the Ising model, quadratic exponential binary distribution, or Boltzmann machine to include covariates. It can also be viewed as an extension of logistic regression to handle responses that are not independent. Not all authors use exactly the same form of the autologistic regression model. Variations of the model differ in two respects. First, the variable coding—the two numbers used to represent the two possible states of the variables—might differ. Common coding choices are (zero, one and (minus one, plus one. Second, the model might appear in either of two algebraic forms: a standard form, or a recently proposed centered form. Little attention has been paid to the effect of these differences, and the literature shows ambiguity about their importance. It is shown here that changes to either coding or centering in fact produce distinct, non-nested probability models. Theoretical results, numerical studies, and analysis of an ecological data set all show that the differences among the models can be large and practically significant. Understanding the nature of the differences and making appropriate modeling choices can lead to significantly improved autologistic regression analyses. The results strongly suggest that the standard model with plus/minus coding, which we call the symmetric autologistic model, is the most natural choice among the autologistic variants.

  1. A spatio-temporal nonparametric Bayesian variable selection model of fMRI data for clustering correlated time courses.

    Science.gov (United States)

    Zhang, Linlin; Guindani, Michele; Versace, Francesco; Vannucci, Marina

    2014-07-15

    In this paper we present a novel wavelet-based Bayesian nonparametric regression model for the analysis of functional magnetic resonance imaging (fMRI) data. Our goal is to provide a joint analytical framework that allows to detect regions of the brain which exhibit neuronal activity in response to a stimulus and, simultaneously, infer the association, or clustering, of spatially remote voxels that exhibit fMRI time series with similar characteristics. We start by modeling the data with a hemodynamic response function (HRF) with a voxel-dependent shape parameter. We detect regions of the brain activated in response to a given stimulus by using mixture priors with a spike at zero on the coefficients of the regression model. We account for the complex spatial correlation structure of the brain by using a Markov random field (MRF) prior on the parameters guiding the selection of the activated voxels, therefore capturing correlation among nearby voxels. In order to infer association of the voxel time courses, we assume correlated errors, in particular long memory, and exploit the whitening properties of discrete wavelet transforms. Furthermore, we achieve clustering of the voxels by imposing a Dirichlet process (DP) prior on the parameters of the long memory process. For inference, we use Markov Chain Monte Carlo (MCMC) sampling techniques that combine Metropolis-Hastings schemes employed in Bayesian variable selection with sampling algorithms for nonparametric DP models. We explore the performance of the proposed model on simulated data, with both block- and event-related design, and on real fMRI data. Copyright © 2014 Elsevier Inc. All rights reserved.

  2. Prediction of retention indices for frequently reported compounds of plant essential oils using multiple linear regression, partial least squares, and support vector machine.

    Science.gov (United States)

    Yan, Jun; Huang, Jian-Hua; He, Min; Lu, Hong-Bing; Yang, Rui; Kong, Bo; Xu, Qing-Song; Liang, Yi-Zeng

    2013-08-01

    Retention indices for frequently reported compounds of plant essential oils on three different stationary phases were investigated. Multivariate linear regression, partial least squares, and support vector machine combined with a new variable selection approach called random-frog recently proposed by our group, were employed to model quantitative structure-retention relationships. Internal and external validations were performed to ensure the stability and predictive ability. All the three methods could obtain an acceptable model, and the optimal results by support vector machine based on a small number of informative descriptors with the square of correlation coefficient for cross validation, values of 0.9726, 0.9759, and 0.9331 on the dimethylsilicone stationary phase, the dimethylsilicone phase with 5% phenyl groups, and the PEG stationary phase, respectively. The performances of two variable selection approaches, random-frog and genetic algorithm, are compared. The importance of the variables was found to be consistent when estimated from correlation coefficients in multivariate linear regression equations and selection probability in model spaces. © 2013 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

  3. FCERI AND HISTAMINE METABOLISM GENE VARIABILITY IN SELECTIVE RESPONDERS TO NSAIDS

    Directory of Open Access Journals (Sweden)

    Gemma Amo

    2016-09-01

    Full Text Available The high-affinity IgE receptor (Fcε RI is a heterotetramer of three subunits: Fcε RIα, Fcε RIβ and Fcε RIγ (αβγ2 encoded by three genes designated as FCER1A, FCER1B (MS4A2 and FCER1G, respectively. Recent evidence points to FCERI gene variability as a relevant factor in the risk of developing allergic diseases. Because Fcε RI plays a key role in the events downstream of the triggering factors in immunological response, we hypothesized that FCERI gene variants might be related with the risk of, or with the clinical response to, selective (IgE mediated non-steroidal anti-inflammatory (NSAID hypersensitivity.From a cohort of 314 patients suffering from selective hypersensitivity to metamizole, ibuprofen, diclofenac, paracetamol, acetylsalicylic acid (ASA, propifenazone, naproxen, ketoprofen, dexketoprofen, etofenamate, aceclofenac, etoricoxib, dexibuprofen, indomethacin, oxyphenylbutazone or piroxicam, and 585 unrelated healthy controls that tolerated these NSAIDs, we analyzed the putative effects of the FCERI SNPs FCER1A rs2494262, rs2427837 and rs2251746; FCER1B rs1441586, rs569108 and rs512555; FCER1G rs11587213, rs2070901 and rs11421. Furthermore, in order to identify additional genetic markers which might be associated with the risk of developing selective NSAID hypersensitivity, or which may modify the putative association of FCERI gene variations with risk, we analyzed polymorphisms known to affect histamine synthesis or metabolism, such as rs17740607, rs2073440, rs1801105, rs2052129, rs10156191, rs1049742 and rs1049793 in the HDC, HNMT and DAO genes.No major genetic associations with risk or with clinical presentation, and no gene-gene interactions, or gene-phenotype interactions (including age, gender, IgE concentration, antecedents of atopy, culprit drug or clinical presentation were identified in patients. However, logistic regression analyses indicated that the presence of antecedents of atopy and the DAO SNP rs2052129 (GG

  4. A rotor optimization using regression analysis

    Science.gov (United States)

    Giansante, N.

    1984-01-01

    The design and development of helicopter rotors is subject to the many design variables and their interactions that effect rotor operation. Until recently, selection of rotor design variables to achieve specified rotor operational qualities has been a costly, time consuming, repetitive task. For the past several years, Kaman Aerospace Corporation has successfully applied multiple linear regression analysis, coupled with optimization and sensitivity procedures, in the analytical design of rotor systems. It is concluded that approximating equations can be developed rapidly for a multiplicity of objective and constraint functions and optimizations can be performed in a rapid and cost effective manner; the number and/or range of design variables can be increased by expanding the data base and developing approximating functions to reflect the expanded design space; the order of the approximating equations can be expanded easily to improve correlation between analyzer results and the approximating equations; gradients of the approximating equations can be calculated easily and these gradients are smooth functions reducing the risk of numerical problems in the optimization; the use of approximating functions allows the problem to be started easily and rapidly from various initial designs to enhance the probability of finding a global optimum; and the approximating equations are independent of the analysis or optimization codes used.

  5. Automatic variable selection method and a comparison for quantitative analysis in laser-induced breakdown spectroscopy

    Science.gov (United States)

    Duan, Fajie; Fu, Xiao; Jiang, Jiajia; Huang, Tingting; Ma, Ling; Zhang, Cong

    2018-05-01

    In this work, an automatic variable selection method for quantitative analysis of soil samples using laser-induced breakdown spectroscopy (LIBS) is proposed, which is based on full spectrum correction (FSC) and modified iterative predictor weighting-partial least squares (mIPW-PLS). The method features automatic selection without artificial processes. To illustrate the feasibility and effectiveness of the method, a comparison with genetic algorithm (GA) and successive projections algorithm (SPA) for different elements (copper, barium and chromium) detection in soil was implemented. The experimental results showed that all the three methods could accomplish variable selection effectively, among which FSC-mIPW-PLS required significantly shorter computation time (12 s approximately for 40,000 initial variables) than the others. Moreover, improved quantification models were got with variable selection approaches. The root mean square errors of prediction (RMSEP) of models utilizing the new method were 27.47 (copper), 37.15 (barium) and 39.70 (chromium) mg/kg, which showed comparable prediction effect with GA and SPA.

  6. Using the Ridge Regression Procedures to Estimate the Multiple Linear Regression Coefficients

    Science.gov (United States)

    Gorgees, HazimMansoor; Mahdi, FatimahAssim

    2018-05-01

    This article concerns with comparing the performance of different types of ordinary ridge regression estimators that have been already proposed to estimate the regression parameters when the near exact linear relationships among the explanatory variables is presented. For this situations we employ the data obtained from tagi gas filling company during the period (2008-2010). The main result we reached is that the method based on the condition number performs better than other methods since it has smaller mean square error (MSE) than the other stated methods.

  7. A Robust Supervised Variable Selection for Noisy High-Dimensional Data

    Czech Academy of Sciences Publication Activity Database

    Kalina, Jan; Schlenker, Anna

    2015-01-01

    Roč. 2015, Article 320385 (2015), s. 1-10 ISSN 2314-6133 R&D Projects: GA ČR GA13-17187S Institutional support: RVO:67985807 Keywords : dimensionality reduction * variable selection * robustness Subject RIV: BA - General Mathematics Impact factor: 2.134, year: 2015

  8. Implicit collinearity effect in linear regression: Application to basal ...

    African Journals Online (AJOL)

    Collinearity of predictor variables is a severe problem in the least square regression analysis. It contributes to the instability of regression coefficients and leads to a wrong prediction accuracy. Despite these problems, studies are conducted with a large number of observed and derived variables linked with a response ...

  9. Multivariate Linear Regression and CART Regression Analysis of TBM Performance at Abu Hamour Phase-I Tunnel

    Science.gov (United States)

    Jakubowski, J.; Stypulkowski, J. B.; Bernardeau, F. G.

    2017-12-01

    The first phase of the Abu Hamour drainage and storm tunnel was completed in early 2017. The 9.5 km long, 3.7 m diameter tunnel was excavated with two Earth Pressure Balance (EPB) Tunnel Boring Machines from Herrenknecht. TBM operation processes were monitored and recorded by Data Acquisition and Evaluation System. The authors coupled collected TBM drive data with available information on rock mass properties, cleansed, completed with secondary variables and aggregated by weeks and shifts. Correlations and descriptive statistics charts were examined. Multivariate Linear Regression and CART regression tree models linking TBM penetration rate (PR), penetration per revolution (PPR) and field penetration index (FPI) with TBM operational and geotechnical characteristics were performed for the conditions of the weak/soft rock of Doha. Both regression methods are interpretable and the data were screened with different computational approaches allowing enriched insight. The primary goal of the analysis was to investigate empirical relations between multiple explanatory and responding variables, to search for best subsets of explanatory variables and to evaluate the strength of linear and non-linear relations. For each of the penetration indices, a predictive model coupling both regression methods was built and validated. The resultant models appeared to be stronger than constituent ones and indicated an opportunity for more accurate and robust TBM performance predictions.

  10. Comparison of Classical Linear Regression and Orthogonal Regression According to the Sum of Squares Perpendicular Distances

    OpenAIRE

    KELEŞ, Taliha; ALTUN, Murat

    2016-01-01

    Regression analysis is a statistical technique for investigating and modeling the relationship between variables. The purpose of this study was the trivial presentation of the equation for orthogonal regression (OR) and the comparison of classical linear regression (CLR) and OR techniques with respect to the sum of squared perpendicular distances. For that purpose, the analyses were shown by an example. It was found that the sum of squared perpendicular distances of OR is smaller. Thus, it wa...

  11. Modelling the co-evolution of indirect genetic effects and inherited variability.

    Science.gov (United States)

    Marjanovic, Jovana; Mulder, Han A; Rönnegård, Lars; Bijma, Piter

    2018-03-28

    When individuals interact, their phenotypes may be affected not only by their own genes but also by genes in their social partners. This phenomenon is known as Indirect Genetic Effects (IGEs). In aquaculture species and some plants, however, competition not only affects trait levels of individuals, but also inflates variability of trait values among individuals. In the field of quantitative genetics, the variability of trait values has been studied as a quantitative trait in itself, and is often referred to as inherited variability. Such studies, however, consider only the genetic effect of the focal individual on trait variability and do not make a connection to competition. Although the observed phenotypic relationship between competition and variability suggests an underlying genetic relationship, the current quantitative genetic models of IGE and inherited variability do not allow for such a relationship. The lack of quantitative genetic models that connect IGEs to inherited variability limits our understanding of the potential of variability to respond to selection, both in nature and agriculture. Models of trait levels, for example, show that IGEs may considerably change heritable variation in trait values. Currently, we lack the tools to investigate whether this result extends to variability of trait values. Here we present a model that integrates IGEs and inherited variability. In this model, the target phenotype, say growth rate, is a function of the genetic and environmental effects of the focal individual and of the difference in trait value between the social partner and the focal individual, multiplied by a regression coefficient. The regression coefficient is a genetic trait, which is a measure of cooperation; a negative value indicates competition, a positive value cooperation, and an increasing value due to selection indicates the evolution of cooperation. In contrast to the existing quantitative genetic models, our model allows for co-evolution of

  12. Survival Prediction and Feature Selection in Patients with Breast Cancer Using Support Vector Regression

    Directory of Open Access Journals (Sweden)

    Shahrbanoo Goli

    2016-01-01

    Full Text Available The Support Vector Regression (SVR model has been broadly used for response prediction. However, few researchers have used SVR for survival analysis. In this study, a new SVR model is proposed and SVR with different kernels and the traditional Cox model are trained. The models are compared based on different performance measures. We also select the best subset of features using three feature selection methods: combination of SVR and statistical tests, univariate feature selection based on concordance index, and recursive feature elimination. The evaluations are performed using available medical datasets and also a Breast Cancer (BC dataset consisting of 573 patients who visited the Oncology Clinic of Hamadan province in Iran. Results show that, for the BC dataset, survival time can be predicted more accurately by linear SVR than nonlinear SVR. Based on the three feature selection methods, metastasis status, progesterone receptor status, and human epidermal growth factor receptor 2 status are the best features associated to survival. Also, according to the obtained results, performance of linear and nonlinear kernels is comparable. The proposed SVR model performs similar to or slightly better than other models. Also, SVR performs similar to or better than Cox when all features are included in model.

  13. Is DAS28-CRP with three and four variables interchangeable in individual patients selected for biological treatment in daily clinical practice?

    DEFF Research Database (Denmark)

    Madsen, Ole Rintek

    2011-01-01

    DAS28 is a widely used composite score for the assessment of disease activity in patients with rheumatoid arthritis (RA) and is often used as a treatment decision tool in the daily clinic. Different versions of DAS28 are available. DAS28-CRP(3) is calculated based on three variables: swollen...... and tender joint counts and CRP. DAS28-CRP(4) also includes patient global assessment. Thresholds for low and high disease activity are the same for the two scores. Based on the Bland-Altman method, the interchangeability between DAS28-CRP with three and four variables was examined in 319 RA patients...... selected for initiating biological treatment. Data were extracted from the Danish registry for biological treatment in rheumatology (DANBIO). Multiple regression analysis was used to assess the predictability of the DAS28 scores by several measures of disease activity. The overall mean DAS28-CRP was 4...

  14. Variable selection in the explorative analysis of several data blocks in metabolomics

    DEFF Research Database (Denmark)

    Karaman, İbrahim; Nørskov, Natalja; Yde, Christian Clement

    highly correlated data sets in one integrated approach. Due to the high number of variables in data sets from metabolomics (both raw data and after peak picking) the selection of important variables in an explorative analysis is difficult, especially when different data sets of metabolomics data need...... to be related. Tools for the handling of mental overflow minimising false discovery rates both by using statistical and biological validation in an integrative approach are needed. In this paper different strategies for variable selection were considered with respect to false discovery and the possibility...... for biological validation. The data set used in this study is metabolomics data from an animal intervention study. The aim of the metabolomics study was to investigate the metabolic profile in pigs fed various cereal fractions with special attention to the metabolism of lignans using NMR and LC-MS based...

  15. EFFECT OF CORE TRAINING ON SELECTED HEMATOLOGICAL VARIABLES AMONG BASKETBALL PLAYERS

    OpenAIRE

    K. Rejinadevi; Dr. C. Ramesh

    2017-01-01

    The purpose of the study was to find out the effect of core training on selected haematological variables among basketball players. For the purpose of the study forty men basketball players were selected as subjects from S.V.N College and Arul Anandar College, Madurai, Tamilnadu at random and their age ranged from 18 to 25 years. The selected subjects are divided in to two groups of twenty subjects each. Group I acted as core training group and Group II acted as control group. The experimenta...

  16. Prediction of Currency Volume Issued in Taiwan Using a Hybrid Artificial Neural Network and Multiple Regression Approach

    Directory of Open Access Journals (Sweden)

    Yuehjen E. Shao

    2013-01-01

    Full Text Available Because the volume of currency issued by a country always affects its interest rate, price index, income levels, and many other important macroeconomic variables, the prediction of currency volume issued has attracted considerable attention in recent years. In contrast to the typical single-stage forecast model, this study proposes a hybrid forecasting approach to predict the volume of currency issued in Taiwan. The proposed hybrid models consist of artificial neural network (ANN and multiple regression (MR components. The MR component of the hybrid models is established for a selection of fewer explanatory variables, wherein the selected variables are of higher importance. The ANN component is then designed to generate forecasts based on those important explanatory variables. Subsequently, the model is used to analyze a real dataset of Taiwan's currency from 1996 to 2011 and twenty associated explanatory variables. The prediction results reveal that the proposed hybrid scheme exhibits superior forecasting performance for predicting the volume of currency issued in Taiwan.

  17. Comparison of cranial sex determination by discriminant analysis and logistic regression.

    Science.gov (United States)

    Amores-Ampuero, Anabel; Alemán, Inmaculada

    2016-04-05

    Various methods have been proposed for estimating dimorphism. The objective of this study was to compare sex determination results from cranial measurements using discriminant analysis or logistic regression. The study sample comprised 130 individuals (70 males) of known sex, age, and cause of death from San José cemetery in Granada (Spain). Measurements of 19 neurocranial dimensions and 11 splanchnocranial dimensions were subjected to discriminant analysis and logistic regression, and the percentages of correct classification were compared between the sex functions obtained with each method. The discriminant capacity of the selected variables was evaluated with a cross-validation procedure. The percentage accuracy with discriminant analysis was 78.2% for the neurocranium (82.4% in females and 74.6% in males) and 73.7% for the splanchnocranium (79.6% in females and 68.8% in males). These percentages were higher with logistic regression analysis: 85.7% for the neurocranium (in both sexes) and 94.1% for the splanchnocranium (100% in females and 91.7% in males).

  18. Application of logistic regression for landslide susceptibility zoning of Cekmece Area, Istanbul, Turkey

    Science.gov (United States)

    Duman, T. Y.; Can, T.; Gokceoglu, C.; Nefeslioglu, H. A.; Sonmez, H.

    2006-11-01

    As a result of industrialization, throughout the world, cities have been growing rapidly for the last century. One typical example of these growing cities is Istanbul, the population of which is over 10 million. Due to rapid urbanization, new areas suitable for settlement and engineering structures are necessary. The Cekmece area located west of the Istanbul metropolitan area is studied, because the landslide activity is extensive in this area. The purpose of this study is to develop a model that can be used to characterize landslide susceptibility in map form using logistic regression analysis of an extensive landslide database. A database of landslide activity was constructed using both aerial-photography and field studies. About 19.2% of the selected study area is covered by deep-seated landslides. The landslides that occur in the area are primarily located in sandstones with interbedded permeable and impermeable layers such as claystone, siltstone and mudstone. About 31.95% of the total landslide area is located at this unit. To apply logistic regression analyses, a data matrix including 37 variables was constructed. The variables used in the forwards stepwise analyses are different measures of slope, aspect, elevation, stream power index (SPI), plan curvature, profile curvature, geology, geomorphology and relative permeability of lithological units. A total of 25 variables were identified as exerting strong influence on landslide occurrence, and included by the logistic regression equation. Wald statistics values indicate that lithology, SPI and slope are more important than the other parameters in the equation. Beta coefficients of the 25 variables included the logistic regression equation provide a model for landslide susceptibility in the Cekmece area. This model is used to generate a landslide susceptibility map that correctly classified 83.8% of the landslide-prone areas.

  19. Retrieving relevant factors with exploratory SEM and principal-covariate regression: A comparison.

    Science.gov (United States)

    Vervloet, Marlies; Van den Noortgate, Wim; Ceulemans, Eva

    2018-02-12

    Behavioral researchers often linearly regress a criterion on multiple predictors, aiming to gain insight into the relations between the criterion and predictors. Obtaining this insight from the ordinary least squares (OLS) regression solution may be troublesome, because OLS regression weights show only the effect of a predictor on top of the effects of other predictors. Moreover, when the number of predictors grows larger, it becomes likely that the predictors will be highly collinear, which makes the regression weights' estimates unstable (i.e., the "bouncing beta" problem). Among other procedures, dimension-reduction-based methods have been proposed for dealing with these problems. These methods yield insight into the data by reducing the predictors to a smaller number of summarizing variables and regressing the criterion on these summarizing variables. Two promising methods are principal-covariate regression (PCovR) and exploratory structural equation modeling (ESEM). Both simultaneously optimize reduction and prediction, but they are based on different frameworks. The resulting solutions have not yet been compared; it is thus unclear what the strengths and weaknesses are of both methods. In this article, we focus on the extents to which PCovR and ESEM are able to extract the factors that truly underlie the predictor scores and can predict a single criterion. The results of two simulation studies showed that for a typical behavioral dataset, ESEM (using the BIC for model selection) in this regard is successful more often than PCovR. Yet, in 93% of the datasets PCovR performed equally well, and in the case of 48 predictors, 100 observations, and large differences in the strengths of the factors, PCovR even outperformed ESEM.

  20. Linear regression in astronomy. I

    Science.gov (United States)

    Isobe, Takashi; Feigelson, Eric D.; Akritas, Michael G.; Babu, Gutti Jogesh

    1990-01-01

    Five methods for obtaining linear regression fits to bivariate data with unknown or insignificant measurement errors are discussed: ordinary least-squares (OLS) regression of Y on X, OLS regression of X on Y, the bisector of the two OLS lines, orthogonal regression, and 'reduced major-axis' regression. These methods have been used by various researchers in observational astronomy, most importantly in cosmic distance scale applications. Formulas for calculating the slope and intercept coefficients and their uncertainties are given for all the methods, including a new general form of the OLS variance estimates. The accuracy of the formulas was confirmed using numerical simulations. The applicability of the procedures is discussed with respect to their mathematical properties, the nature of the astronomical data under consideration, and the scientific purpose of the regression. It is found that, for problems needing symmetrical treatment of the variables, the OLS bisector performs significantly better than orthogonal or reduced major-axis regression.

  1. Logistic regression accuracy across different spatial and temporal scales for a wide-ranging species, the marbled murrelet

    Science.gov (United States)

    Carolyn B. Meyer; Sherri L. Miller; C. John Ralph

    2004-01-01

    The scale at which habitat variables are measured affects the accuracy of resource selection functions in predicting animal use of sites. We used logistic regression models for a wide-ranging species, the marbled murrelet, (Brachyramphus marmoratus) in a large region in California to address how much changing the spatial or temporal scale of...

  2. How to regress and predict in a Bland-Altman plot? Review and contribution based on tolerance intervals and correlated-errors-in-variables models.

    Science.gov (United States)

    Francq, Bernard G; Govaerts, Bernadette

    2016-06-30

    Two main methodologies for assessing equivalence in method-comparison studies are presented separately in the literature. The first one is the well-known and widely applied Bland-Altman approach with its agreement intervals, where two methods are considered interchangeable if their differences are not clinically significant. The second approach is based on errors-in-variables regression in a classical (X,Y) plot and focuses on confidence intervals, whereby two methods are considered equivalent when providing similar measures notwithstanding the random measurement errors. This paper reconciles these two methodologies and shows their similarities and differences using both real data and simulations. A new consistent correlated-errors-in-variables regression is introduced as the errors are shown to be correlated in the Bland-Altman plot. Indeed, the coverage probabilities collapse and the biases soar when this correlation is ignored. Novel tolerance intervals are compared with agreement intervals with or without replicated data, and novel predictive intervals are introduced to predict a single measure in an (X,Y) plot or in a Bland-Atman plot with excellent coverage probabilities. We conclude that the (correlated)-errors-in-variables regressions should not be avoided in method comparison studies, although the Bland-Altman approach is usually applied to avert their complexity. We argue that tolerance or predictive intervals are better alternatives than agreement intervals, and we provide guidelines for practitioners regarding method comparison studies. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

  3. Prediction accuracy and stability of regression with optimal scaling transformations

    NARCIS (Netherlands)

    Kooij, van der Anita J.

    2007-01-01

    The central topic of this thesis is the CATREG approach to nonlinear regression. This approach finds optimal quantifications for categorical variables and/or nonlinear transformations for numerical variables in regression analysis. (CATREG is implemented in SPSS Categories by the author of the

  4. Comparison of partial least squares and lasso regression techniques as applied to laser-induced breakdown spectroscopy of geological samples

    International Nuclear Information System (INIS)

    Dyar, M.D.; Carmosino, M.L.; Breves, E.A.; Ozanne, M.V.; Clegg, S.M.; Wiens, R.C.

    2012-01-01

    A remote laser-induced breakdown spectrometer (LIBS) designed to simulate the ChemCam instrument on the Mars Science Laboratory Rover Curiosity was used to probe 100 geologic samples at a 9-m standoff distance. ChemCam consists of an integrated remote LIBS instrument that will probe samples up to 7 m from the mast of the rover and a remote micro-imager (RMI) that will record context images. The elemental compositions of 100 igneous and highly-metamorphosed rocks are determined with LIBS using three variations of multivariate analysis, with a goal of improving the analytical accuracy. Two forms of partial least squares (PLS) regression are employed with finely-tuned parameters: PLS-1 regresses a single response variable (elemental concentration) against the observation variables (spectra, or intensity at each of 6144 spectrometer channels), while PLS-2 simultaneously regresses multiple response variables (concentrations of the ten major elements in rocks) against the observation predictor variables, taking advantage of natural correlations between elements. Those results are contrasted with those from the multivariate regression technique of the least absolute shrinkage and selection operator (lasso), which is a penalized shrunken regression method that selects the specific channels for each element that explain the most variance in the concentration of that element. To make this comparison, we use results of cross-validation and of held-out testing, and employ unscaled and uncentered spectral intensity data because all of the input variables are already in the same units. Results demonstrate that the lasso, PLS-1, and PLS-2 all yield comparable results in terms of accuracy for this dataset. However, the interpretability of these methods differs greatly in terms of fundamental understanding of LIBS emissions. PLS techniques generate principal components, linear combinations of intensities at any number of spectrometer channels, which explain as much variance in the

  5. Linear regression in astronomy. II

    Science.gov (United States)

    Feigelson, Eric D.; Babu, Gutti J.

    1992-01-01

    A wide variety of least-squares linear regression procedures used in observational astronomy, particularly investigations of the cosmic distance scale, are presented and discussed. The classes of linear models considered are (1) unweighted regression lines, with bootstrap and jackknife resampling; (2) regression solutions when measurement error, in one or both variables, dominates the scatter; (3) methods to apply a calibration line to new data; (4) truncated regression models, which apply to flux-limited data sets; and (5) censored regression models, which apply when nondetections are present. For the calibration problem we develop two new procedures: a formula for the intercept offset between two parallel data sets, which propagates slope errors from one regression to the other; and a generalization of the Working-Hotelling confidence bands to nonstandard least-squares lines. They can provide improved error analysis for Faber-Jackson, Tully-Fisher, and similar cosmic distance scale relations.

  6. Local Strategy Combined with a Wavelength Selection Method for Multivariate Calibration

    Directory of Open Access Journals (Sweden)

    Haitao Chang

    2016-06-01

    Full Text Available One of the essential factors influencing the prediction accuracy of multivariate calibration models is the quality of the calibration data. A local regression strategy, together with a wavelength selection approach, is proposed to build the multivariate calibration models based on partial least squares regression. The local algorithm is applied to create a calibration set of spectra similar to the spectrum of an unknown sample; the synthetic degree of grey relation coefficient is used to evaluate the similarity. A wavelength selection method based on simple-to-use interactive self-modeling mixture analysis minimizes the influence of noisy variables, and the most informative variables of the most similar samples are selected to build the multivariate calibration model based on partial least squares regression. To validate the performance of the proposed method, ultraviolet-visible absorbance spectra of mixed solutions of food coloring analytes in a concentration range of 20–200 µg/mL is measured. Experimental results show that the proposed method can not only enhance the prediction accuracy of the calibration model, but also greatly reduce its complexity.

  7. Poisson regression for modeling count and frequency outcomes in trauma research.

    Science.gov (United States)

    Gagnon, David R; Doron-LaMarca, Susan; Bell, Margret; O'Farrell, Timothy J; Taft, Casey T

    2008-10-01

    The authors describe how the Poisson regression method for analyzing count or frequency outcome variables can be applied in trauma studies. The outcome of interest in trauma research may represent a count of the number of incidents of behavior occurring in a given time interval, such as acts of physical aggression or substance abuse. Traditional linear regression approaches assume a normally distributed outcome variable with equal variances over the range of predictor variables, and may not be optimal for modeling count outcomes. An application of Poisson regression is presented using data from a study of intimate partner aggression among male patients in an alcohol treatment program and their female partners. Results of Poisson regression and linear regression models are compared.

  8. STEPWISE SELECTION OF VARIABLES IN DEA USING CONTRIBUTION LOADS

    Directory of Open Access Journals (Sweden)

    Fernando Fernandez-Palacin

    Full Text Available ABSTRACT In this paper, we propose a new methodology for variable selection in Data Envelopment Analysis (DEA. The methodology is based on an internal measure which evaluates the contribution of each variable in the calculation of the efficiency scores of DMUs. In order to apply the proposed method, an algorithm, known as “ADEA”, was developed and implemented in R. Step by step, the algorithm maximizes the load of the variable (input or output which contribute least to the calculation of the efficiency scores, redistributing the weights of the variables without altering the efficiency scores of the DMUs. Once the weights have been redistributed, if the lower contribution does not reach a previously given critical value, a variable with minimum contribution will be removed from the model and, as a result, the DEA will be solved again. The algorithm will stop when all variables reach a given contribution load to the DEA or until no more variables can be removed. In this way and contrary to what is usual, the algorithm provides a clear stop rule. In both cases, the efficiencies obtained from the DEA will be considered suitable and rightly interpreted in terms of the remaining variables, indicating the load themselves; moreover, the algorithm will provide a sequence of alternative nested models - potential solutions - that could be evaluated according to external criterion. To illustrate the procedure, we have applied the methodology proposed to obtain a research ranking of Spanish public universities. In this case, at each step of the algorithm, the critical value is obtained based on a simulation study.

  9. Stochastic development regression using method of moments

    DEFF Research Database (Denmark)

    Kühnel, Line; Sommer, Stefan Horst

    2017-01-01

    This paper considers the estimation problem arising when inferring parameters in the stochastic development regression model for manifold valued non-linear data. Stochastic development regression captures the relation between manifold-valued response and Euclidean covariate variables using...... the stochastic development construction. It is thereby able to incorporate several covariate variables and random effects. The model is intrinsically defined using the connection of the manifold, and the use of stochastic development avoids linearizing the geometry. We propose to infer parameters using...... the Method of Moments procedure that matches known constraints on moments of the observations conditional on the latent variables. The performance of the model is investigated in a simulation example using data on finite dimensional landmark manifolds....

  10. Model-based Quantile Regression for Discrete Data

    KAUST Repository

    Padellini, Tullia

    2018-04-10

    Quantile regression is a class of methods voted to the modelling of conditional quantiles. In a Bayesian framework quantile regression has typically been carried out exploiting the Asymmetric Laplace Distribution as a working likelihood. Despite the fact that this leads to a proper posterior for the regression coefficients, the resulting posterior variance is however affected by an unidentifiable parameter, hence any inferential procedure beside point estimation is unreliable. We propose a model-based approach for quantile regression that considers quantiles of the generating distribution directly, and thus allows for a proper uncertainty quantification. We then create a link between quantile regression and generalised linear models by mapping the quantiles to the parameter of the response variable, and we exploit it to fit the model with R-INLA. We extend it also in the case of discrete responses, where there is no 1-to-1 relationship between quantiles and distribution\\'s parameter, by introducing continuous generalisations of the most common discrete variables (Poisson, Binomial and Negative Binomial) to be exploited in the fitting.

  11. Modelling infant mortality rate in Central Java, Indonesia use generalized poisson regression method

    Science.gov (United States)

    Prahutama, Alan; Sudarno

    2018-05-01

    The infant mortality rate is the number of deaths under one year of age occurring among the live births in a given geographical area during a given year, per 1,000 live births occurring among the population of the given geographical area during the same year. This problem needs to be addressed because it is an important element of a country’s economic development. High infant mortality rate will disrupt the stability of a country as it relates to the sustainability of the population in the country. One of regression model that can be used to analyze the relationship between dependent variable Y in the form of discrete data and independent variable X is Poisson regression model. Recently The regression modeling used for data with dependent variable is discrete, among others, poisson regression, negative binomial regression and generalized poisson regression. In this research, generalized poisson regression modeling gives better AIC value than poisson regression. The most significant variable is the Number of health facilities (X1), while the variable that gives the most influence to infant mortality rate is the average breastfeeding (X9).

  12. Improving the Classification Accuracy for Near-Infrared Spectroscopy of Chinese Salvia miltiorrhiza Using Local Variable Selection

    Directory of Open Access Journals (Sweden)

    Lianqing Zhu

    2018-01-01

    Full Text Available In order to improve the classification accuracy of Chinese Salvia miltiorrhiza using near-infrared spectroscopy, a novel local variable selection strategy is thus proposed. Combining the strengths of the local algorithm and interval partial least squares, the spectra data have firstly been divided into several pairs of classes in sample direction and equidistant subintervals in variable direction. Then, a local classification model has been built, and the most proper spectral region has been selected based on the new evaluation criterion considering both classification error rate and best predictive ability under the leave-one-out cross validation scheme for each pair of classes. Finally, each observation can be assigned to belong to the class according to the statistical analysis of classification results of the local classification model built on selected variables. The performance of the proposed method was demonstrated through near-infrared spectra of cultivated or wild Salvia miltiorrhiza, which are collected from 8 geographical origins in 5 provinces of China. For comparison, soft independent modelling of class analogy and partial least squares discriminant analysis methods are, respectively, employed as the classification model. Experimental results showed that classification performance of the classification model with local variable selection was obvious better than that without variable selection.

  13. Regression models to estimate real-time concentrations of selected constituents in two tributaries to Lake Houston near Houston, Texas, 2005-07

    Science.gov (United States)

    Oden, Timothy D.; Asquith, William H.; Milburn, Matthew S.

    2009-01-01

    In December 2005, the U.S. Geological Survey in cooperation with the City of Houston, Texas, began collecting discrete water-quality samples for nutrients, total organic carbon, bacteria (total coliform and Escherichia coli), atrazine, and suspended sediment at two U.S. Geological Survey streamflow-gaging stations upstream from Lake Houston near Houston (08068500 Spring Creek near Spring, Texas, and 08070200 East Fork San Jacinto River near New Caney, Texas). The data from the discrete water-quality samples collected during 2005-07, in conjunction with monitored real-time data already being collected - physical properties (specific conductance, pH, water temperature, turbidity, and dissolved oxygen), streamflow, and rainfall - were used to develop regression models for predicting water-quality constituent concentrations for inflows to Lake Houston. Rainfall data were obtained from a rain gage monitored by Harris County Homeland Security and Emergency Management and colocated with the Spring Creek station. The leaps and bounds algorithm was used to find the best subsets of possible regression models (minimum residual sum of squares for a given number of variables). The potential explanatory or predictive variables included discharge (streamflow), specific conductance, pH, water temperature, turbidity, dissolved oxygen, rainfall, and time (to account for seasonal variations inherent in some water-quality data). The response variables at each site were nitrite plus nitrate nitrogen, total phosphorus, organic carbon, Escherichia coli, atrazine, and suspended sediment. The explanatory variables provide easily measured quantities as a means to estimate concentrations of the various constituents under investigation, with accompanying estimates of measurement uncertainty. Each regression equation can be used to estimate concentrations of a given constituent in real time. In conjunction with estimated concentrations, constituent loads were estimated by multiplying the

  14. Regression with Sparse Approximations of Data

    DEFF Research Database (Denmark)

    Noorzad, Pardis; Sturm, Bob L.

    2012-01-01

    We propose sparse approximation weighted regression (SPARROW), a method for local estimation of the regression function that uses sparse approximation with a dictionary of measurements. SPARROW estimates the regression function at a point with a linear combination of a few regressands selected...... by a sparse approximation of the point in terms of the regressors. We show SPARROW can be considered a variant of \\(k\\)-nearest neighbors regression (\\(k\\)-NNR), and more generally, local polynomial kernel regression. Unlike \\(k\\)-NNR, however, SPARROW can adapt the number of regressors to use based...

  15. Selected Macroeconomic Variables and Stock Market Movements: Empirical evidence from Thailand

    Directory of Open Access Journals (Sweden)

    Joseph Ato Forson

    2014-06-01

    Full Text Available This paper investigates and analyzes the long-run equilibrium relationship between the Thai stock Exchange Index (SETI and selected macroeconomic variables using monthly time series data that cover a 20-year period from January 1990 to December 2009. The following macroeconomic variables are included in our analysis: money supply (MS, the consumer price index (CPI, interest rate (IR and the industrial production index (IP (as a proxy for GDP. Our findings prove that the SET Index and the selected macroeconomic variables are cointegrated at I (1 and have a significant equilibrium relationship over the long run. Money supply demonstrates a strong positive relationship with the SET Index over the long run, whereas the industrial production index and consumer price index show negative long-run relationships with the SET Index. Furthermore, in non-equilibrium situations, the error correction mechanism suggests that the consumer price index, industrial production index and money supply each contribute in some way to restore equilibrium. In addition, using Toda and Yamamoto’s augmented Granger causality test, we identify a bi-causal relationship between industrial production and money supply and unilateral causal relationships between CPI and IR, IP and CPI, MS and CPI, and IP and SETI, indicating that all of these variables are sensitive to Thai stock market movements. The policy implications of these findings are also discussed.

  16. The Effects of Variability and Risk in Selection Utility Analysis: An Empirical Comparison.

    Science.gov (United States)

    Rich, Joseph R.; Boudreau, John W.

    1987-01-01

    Investigated utility estimate variability for the selection utility of using the Programmer Aptitude Test to select computer programmers. Comparison of Monte Carlo results to other risk assessment approaches (sensitivity analysis, break-even analysis, algebraic derivation of the distribtion) suggests that distribution information provided by Monte…

  17. 10 km running performance predicted by a multiple linear regression model with allometrically adjusted variables.

    Science.gov (United States)

    Abad, Cesar C C; Barros, Ronaldo V; Bertuzzi, Romulo; Gagliardi, João F L; Lima-Silva, Adriano E; Lambert, Mike I; Pires, Flavio O

    2016-06-01

    The aim of this study was to verify the power of VO 2max , peak treadmill running velocity (PTV), and running economy (RE), unadjusted or allometrically adjusted, in predicting 10 km running performance. Eighteen male endurance runners performed: 1) an incremental test to exhaustion to determine VO 2max and PTV; 2) a constant submaximal run at 12 km·h -1 on an outdoor track for RE determination; and 3) a 10 km running race. Unadjusted (VO 2max , PTV and RE) and adjusted variables (VO 2max 0.72 , PTV 0.72 and RE 0.60 ) were investigated through independent multiple regression models to predict 10 km running race time. There were no significant correlations between 10 km running time and either the adjusted or unadjusted VO 2max . Significant correlations (p 0.84 and power > 0.88. The allometrically adjusted predictive model was composed of PTV 0.72 and RE 0.60 and explained 83% of the variance in 10 km running time with a standard error of the estimate (SEE) of 1.5 min. The unadjusted model composed of a single PVT accounted for 72% of the variance in 10 km running time (SEE of 1.9 min). Both regression models provided powerful estimates of 10 km running time; however, the unadjusted PTV may provide an uncomplicated estimation.

  18. Predictive-property-ranked variable reduction in partial least squares modelling with final complexity adapted models: comparison of properties for ranking.

    Science.gov (United States)

    Andries, Jan P M; Vander Heyden, Yvan; Buydens, Lutgarde M C

    2013-01-14

    The calibration performance of partial least squares regression for one response (PLS1) can be improved by eliminating uninformative variables. Many variable-reduction methods are based on so-called predictor-variable properties or predictive properties, which are functions of various PLS-model parameters, and which may change during the steps of the variable-reduction process. Recently, a new predictive-property-ranked variable reduction method with final complexity adapted models, denoted as PPRVR-FCAM or simply FCAM, was introduced. It is a backward variable elimination method applied on the predictive-property-ranked variables. The variable number is first reduced, with constant PLS1 model complexity A, until A variables remain, followed by a further decrease in PLS complexity, allowing the final selection of small numbers of variables. In this study for three data sets the utility and effectiveness of six individual and nine combined predictor-variable properties are investigated, when used in the FCAM method. The individual properties include the absolute value of the PLS1 regression coefficient (REG), the significance of the PLS1 regression coefficient (SIG), the norm of the loading weight (NLW) vector, the variable importance in the projection (VIP), the selectivity ratio (SR), and the squared correlation coefficient of a predictor variable with the response y (COR). The selective and predictive performances of the models resulting from the use of these properties are statistically compared using the one-tailed Wilcoxon signed rank test. The results indicate that the models, resulting from variable reduction with the FCAM method, using individual or combined properties, have similar or better predictive abilities than the full spectrum models. After mean-centring of the data, REG and SIG, provide low numbers of informative variables, with a meaning relevant to the response, and lower than the other individual properties, while the predictive abilities are

  19. Association of footprint measurements with plantar kinetics: a linear regression model.

    Science.gov (United States)

    Fascione, Jeanna M; Crews, Ryan T; Wrobel, James S

    2014-03-01

    The use of foot measurements to classify morphology and interpret foot function remains one of the focal concepts of lower-extremity biomechanics. However, only 27% to 55% of midfoot variance in foot pressures has been determined in the most comprehensive models. We investigated whether dynamic walking footprint measurements are associated with inter-individual foot loading variability. Thirty individuals (15 men and 15 women; mean ± SD age, 27.17 ± 2.21 years) walked at a self-selected speed over an electronic pedography platform using the midgait technique. Kinetic variables (contact time, peak pressure, pressure-time integral, and force-time integral) were collected for six masked regions. Footprints were digitized for area and linear boundaries using digital photo planimetry software. Six footprint measurements were determined: contact area, footprint index, arch index, truncated arch index, Chippaux-Smirak index, and Staheli index. Linear regression analysis with a Bonferroni adjustment was performed to determine the association between the footprint measurements and each of the kinetic variables. The findings demonstrate that a relationship exists between increased midfoot contact and increased kinetic values in respective locations. Many of these variables produced large effect sizes while describing 38% to 71% of the common variance of select plantar kinetic variables in the medial midfoot region. In addition, larger footprints were associated with larger kinetic values at the medial heel region and both masked forefoot regions. Dynamic footprint measurements are associated with dynamic plantar loading kinetics, with emphasis on the midfoot region.

  20. The M Word: Multicollinearity in Multiple Regression.

    Science.gov (United States)

    Morrow-Howell, Nancy

    1994-01-01

    Notes that existence of substantial correlation between two or more independent variables creates problems of multicollinearity in multiple regression. Discusses multicollinearity problem in social work research in which independent variables are usually intercorrelated. Clarifies problems created by multicollinearity, explains detection of…

  1. Two Paradoxes in Linear Regression Analysis

    Science.gov (United States)

    FENG, Ge; PENG, Jing; TU, Dongke; ZHENG, Julia Z.; FENG, Changyong

    2016-01-01

    Summary Regression is one of the favorite tools in applied statistics. However, misuse and misinterpretation of results from regression analysis are common in biomedical research. In this paper we use statistical theory and simulation studies to clarify some paradoxes around this popular statistical method. In particular, we show that a widely used model selection procedure employed in many publications in top medical journals is wrong. Formal procedures based on solid statistical theory should be used in model selection. PMID:28638214

  2. Comparing Kriging and Regression Approaches for Mapping Soil Clay Content in a diverse Danish Landscape

    DEFF Research Database (Denmark)

    Adhikari, Kabindra; Bou Kheir, Rania; Greve, Mette Balslev

    2013-01-01

    Information on the spatial variability of soil texture including soil clay content in a landscape is very important for agricultural and environmental use. Different prediction techniques are available to assess and map spatial variability of soil properties, but selecting the most suitable techn...... the prediction in OKst compared with that in OK, whereas RT showed the lowest performance of all (R2 = 0.52; RMSE = 0.52; and RPD = 1.17). We found RKrr to be an effective prediction method and recommend this method for any future soil mapping activities in Denmark....... technique at a given site has always been a major issue in all soil mapping applications. We studied the prediction performance of ordinary kriging (OK), stratified OK (OKst), regression trees (RT), and rule-based regression kriging (RKrr) for digital mapping of soil clay content at 30.4-m grid size using 6...

  3. Identification of solid state fermentation degree with FT-NIR spectroscopy: Comparison of wavelength variable selection methods of CARS and SCARS

    Science.gov (United States)

    Jiang, Hui; Zhang, Hang; Chen, Quansheng; Mei, Congli; Liu, Guohai

    2015-10-01

    The use of wavelength variable selection before partial least squares discriminant analysis (PLS-DA) for qualitative identification of solid state fermentation degree by FT-NIR spectroscopy technique was investigated in this study. Two wavelength variable selection methods including competitive adaptive reweighted sampling (CARS) and stability competitive adaptive reweighted sampling (SCARS) were employed to select the important wavelengths. PLS-DA was applied to calibrate identified model using selected wavelength variables by CARS and SCARS for identification of solid state fermentation degree. Experimental results showed that the number of selected wavelength variables by CARS and SCARS were 58 and 47, respectively, from the 1557 original wavelength variables. Compared with the results of full-spectrum PLS-DA, the two wavelength variable selection methods both could enhance the performance of identified models. Meanwhile, compared with CARS-PLS-DA model, the SCARS-PLS-DA model achieved better results with the identification rate of 91.43% in the validation process. The overall results sufficiently demonstrate the PLS-DA model constructed using selected wavelength variables by a proper wavelength variable method can be more accurate identification of solid state fermentation degree.

  4. Impact of Psychological Variables on Playing Ability of University Level Soccer Players

    Directory of Open Access Journals (Sweden)

    Ertan Tufekcioglu

    2014-10-01

    Full Text Available The purpose of the study was to find out the relationship between psychological variables and soccer playing ability among the university level male players. 42 soccer players representing different universities who participated in inter university competitions were selected as the subjects of the study. The dependent variable was soccer playing ability and independent variables were the selected psychological variables. Soccer playing ability was determined through a 10 point scale at the time of competitions. Psychological variables included achievement motivation, anxiety, self-concept and aggression. The data was statistically analyzed using Karl Pearson’s correlation coefficient and multiple regression analysis using SPSS. It was concluded that soccer playing ability has a positive correlation with achievement motivation and self-concept whereas anxiety and aggression have a negative correlation with soccer playing ability.

  5. Inference for feature selection using the Lasso with high-dimensional data

    DEFF Research Database (Denmark)

    Brink-Jensen, Kasper; Ekstrøm, Claus Thorn

    2014-01-01

    Penalized regression models such as the Lasso have proved useful for variable selection in many fields - especially for situations with high-dimensional data where the numbers of predictors far exceeds the number of observations. These methods identify and rank variables of importance but do...... not generally provide any inference of the selected variables. Thus, the variables selected might be the "most important" but need not be significant. We propose a significance test for the selection found by the Lasso. We introduce a procedure that computes inference and p-values for features chosen...... by the Lasso. This method rephrases the null hypothesis and uses a randomization approach which ensures that the error rate is controlled even for small samples. We demonstrate the ability of the algorithm to compute $p$-values of the expected magnitude with simulated data using a multitude of scenarios...

  6. Isoenzymatic variability in tropical maize populations under reciprocal recurrent selection

    Directory of Open Access Journals (Sweden)

    Pinto Luciana Rossini

    2003-01-01

    Full Text Available Maize (Zea mays L. is one of the crops in which the genetic variability has been extensively studied at isoenzymatic loci. The genetic variability of the maize populations BR-105 and BR-106, and the synthetics IG-3 and IG-4, obtained after one cycle of a high-intensity reciprocal recurrent selection (RRS, was investigated at seven isoenzymatic loci. A total of twenty alleles were identified, and most of the private alleles were found in the BR-106 population. One cycle of reciprocal recurrent selection (RRS caused reductions of 12% in the number of alleles in both populations. Changes in allele frequencies were also observed between populations and synthetics, mainly for the Est 2 locus. Populations presented similar values for the number of alleles per locus, percentage of polymorphic loci, and observed and expected heterozygosities. A decrease of the genetic variation values was observed for the synthetics as a consequence of genetic drift effects and reduction of the effective population sizes. The distribution of the genetic diversity within and between populations revealed that most of the diversity was maintained within them, i.e. BR-105 x BR-106 (G ST = 3.5% and IG-3 x IG-4 (G ST = 4.0%. The genetic distances between populations and synthetics increased approximately 21%. An increase in the genetic divergence between the populations occurred without limiting new selection procedures.

  7. Ridge Regression and Other Kernels for Genomic Selection with R Package rrBLUP

    Directory of Open Access Journals (Sweden)

    Jeffrey B. Endelman

    2011-11-01

    Full Text Available Many important traits in plant breeding are polygenic and therefore recalcitrant to traditional marker-assisted selection. Genomic selection addresses this complexity by including all markers in the prediction model. A key method for the genomic prediction of breeding values is ridge regression (RR, which is equivalent to best linear unbiased prediction (BLUP when the genetic covariance between lines is proportional to their similarity in genotype space. This additive model can be broadened to include epistatic effects by using other kernels, such as the Gaussian, which represent inner products in a complex feature space. To facilitate the use of RR and nonadditive kernels in plant breeding, a new software package for R called rrBLUP has been developed. At its core is a fast maximum-likelihood algorithm for mixed models with a single variance component besides the residual error, which allows for efficient prediction with unreplicated training data. Use of the rrBLUP software is demonstrated through several examples, including the identification of optimal crosses based on superior progeny value. In cross-validation tests, the prediction accuracy with nonadditive kernels was significantly higher than RR for wheat ( L. grain yield but equivalent for several maize ( L. traits.

  8. Bounded Gaussian process regression

    DEFF Research Database (Denmark)

    Jensen, Bjørn Sand; Nielsen, Jens Brehm; Larsen, Jan

    2013-01-01

    We extend the Gaussian process (GP) framework for bounded regression by introducing two bounded likelihood functions that model the noise on the dependent variable explicitly. This is fundamentally different from the implicit noise assumption in the previously suggested warped GP framework. We...... with the proposed explicit noise-model extension....

  9. Multivariate fault isolation of batch processes via variable selection in partial least squares discriminant analysis.

    Science.gov (United States)

    Yan, Zhengbing; Kuang, Te-Hui; Yao, Yuan

    2017-09-01

    In recent years, multivariate statistical monitoring of batch processes has become a popular research topic, wherein multivariate fault isolation is an important step aiming at the identification of the faulty variables contributing most to the detected process abnormality. Although contribution plots have been commonly used in statistical fault isolation, such methods suffer from the smearing effect between correlated variables. In particular, in batch process monitoring, the high autocorrelations and cross-correlations that exist in variable trajectories make the smearing effect unavoidable. To address such a problem, a variable selection-based fault isolation method is proposed in this research, which transforms the fault isolation problem into a variable selection problem in partial least squares discriminant analysis and solves it by calculating a sparse partial least squares model. As different from the traditional methods, the proposed method emphasizes the relative importance of each process variable. Such information may help process engineers in conducting root-cause diagnosis. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

  10. Data re-arranging techniques leading to proper variable selections in high energy physics

    Science.gov (United States)

    Kůs, Václav; Bouř, Petr

    2017-12-01

    We introduce a new data based approach to homogeneity testing and variable selection carried out in high energy physics experiments, where one of the basic tasks is to test the homogeneity of weighted samples, mainly the Monte Carlo simulations (weighted) and real data measurements (unweighted). This technique is called ’data re-arranging’ and it enables variable selection performed by means of the classical statistical homogeneity tests such as Kolmogorov-Smirnov, Anderson-Darling, or Pearson’s chi-square divergence test. P-values of our variants of homogeneity tests are investigated and the empirical verification through 46 dimensional high energy particle physics data sets is accomplished under newly proposed (equiprobable) quantile binning. Particularly, the procedure of homogeneity testing is applied to re-arranged Monte Carlo samples and real DATA sets measured at the particle accelerator Tevatron in Fermilab at DØ experiment originating from top-antitop quark pair production in two decay channels (electron, muon) with 2, 3, or 4+ jets detected. Finally, the variable selections in the electron and muon channels induced by the re-arranging procedure for homogeneity testing are provided for Tevatron top-antitop quark data sets.

  11. Machine learning search for variable stars

    Science.gov (United States)

    Pashchenko, Ilya N.; Sokolovsky, Kirill V.; Gavras, Panagiotis

    2018-04-01

    Photometric variability detection is often considered as a hypothesis testing problem: an object is variable if the null hypothesis that its brightness is constant can be ruled out given the measurements and their uncertainties. The practical applicability of this approach is limited by uncorrected systematic errors. We propose a new variability detection technique sensitive to a wide range of variability types while being robust to outliers and underestimated measurement uncertainties. We consider variability detection as a classification problem that can be approached with machine learning. Logistic Regression (LR), Support Vector Machines (SVM), k Nearest Neighbours (kNN), Neural Nets (NN), Random Forests (RF), and Stochastic Gradient Boosting classifier (SGB) are applied to 18 features (variability indices) quantifying scatter and/or correlation between points in a light curve. We use a subset of Optical Gravitational Lensing Experiment phase two (OGLE-II) Large Magellanic Cloud (LMC) photometry (30 265 light curves) that was searched for variability using traditional methods (168 known variable objects) as the training set and then apply the NN to a new test set of 31 798 OGLE-II LMC light curves. Among 205 candidates selected in the test set, 178 are real variables, while 13 low-amplitude variables are new discoveries. The machine learning classifiers considered are found to be more efficient (select more variables and fewer false candidates) compared to traditional techniques using individual variability indices or their linear combination. The NN, SGB, SVM, and RF show a higher efficiency compared to LR and kNN.

  12. Regression tree analysis for predicting body weight of Nigerian Muscovy duck (Cairina moschata

    Directory of Open Access Journals (Sweden)

    Oguntunji Abel Olusegun

    2017-01-01

    Full Text Available Morphometric parameters and their indices are central to the understanding of the type and function of livestock. The present study was conducted to predict body weight (BWT of adult Nigerian Muscovy ducks from nine (9 morphometric parameters and seven (7 body indices and also to identify the most important predictor of BWT among them using regression tree analysis (RTA. The experimental birds comprised of 1,020 adult male and female Nigerian Muscovy ducks randomly sampled in Rain Forest (203, Guinea Savanna (298 and Derived Savanna (519 agro-ecological zones. Result of RTA revealed that compactness; body girth and massiveness were the most important independent variables in predicting BWT and were used in constructing RT. The combined effect of the three predictors was very high and explained 91.00% of the observed variation of the target variable (BWT. The optimal regression tree suggested that Muscovy ducks with compactness >5.765 would be fleshy and have highest BWT. The result of the present study could be exploited by animal breeders and breeding companies in selection and improvement of BWT of Muscovy ducks.

  13. To resuscitate or not to resuscitate: a logistic regression analysis of physician-related variables influencing the decision.

    Science.gov (United States)

    Einav, Sharon; Alon, Gady; Kaufman, Nechama; Braunstein, Rony; Carmel, Sara; Varon, Joseph; Hersch, Moshe

    2012-09-01

    To determine whether variables in physicians' backgrounds influenced their decision to forego resuscitating a patient they did not previously know. Questionnaire survey of a convenience sample of 204 physicians working in the departments of internal medicine, anaesthesiology and cardiology in 11 hospitals in Israel. Twenty per cent of the participants had elected to forego resuscitating a patient they did not previously know without additional consultation. Physicians who had more frequently elected to forego resuscitation had practised medicine for more than 5 years (p=0.013), estimated the number of resuscitations they had performed as being higher (p=0.009), and perceived their experience in resuscitation as sufficient (p=0.001). The variable that predicted the outcome of always performing resuscitation in the logistic regression model was less than 5 years of experience in medicine (OR 0.227, 95% CI 0.065 to 0.793; p=0.02). Physicians' level of experience may affect the probability of a patient's receiving resuscitation, whereas the physicians' personal beliefs and values did not seem to affect this outcome.

  14. Targeting: Logistic Regression, Special Cases and Extensions

    Directory of Open Access Journals (Sweden)

    Helmut Schaeben

    2014-12-01

    Full Text Available Logistic regression is a classical linear model for logit-transformed conditional probabilities of a binary target variable. It recovers the true conditional probabilities if the joint distribution of predictors and the target is of log-linear form. Weights-of-evidence is an ordinary logistic regression with parameters equal to the differences of the weights of evidence if all predictor variables are discrete and conditionally independent given the target variable. The hypothesis of conditional independence can be tested in terms of log-linear models. If the assumption of conditional independence is violated, the application of weights-of-evidence does not only corrupt the predicted conditional probabilities, but also their rank transform. Logistic regression models, including the interaction terms, can account for the lack of conditional independence, appropriate interaction terms compensate exactly for violations of conditional independence. Multilayer artificial neural nets may be seen as nested regression-like models, with some sigmoidal activation function. Most often, the logistic function is used as the activation function. If the net topology, i.e., its control, is sufficiently versatile to mimic interaction terms, artificial neural nets are able to account for violations of conditional independence and yield very similar results. Weights-of-evidence cannot reasonably include interaction terms; subsequent modifications of the weights, as often suggested, cannot emulate the effect of interaction terms.

  15. Assessing the impact of local meteorological variables on surface ozone in Hong Kong during 2000-2015 using quantile and multiple line regression models

    Science.gov (United States)

    Zhao, Wei; Fan, Shaojia; Guo, Hai; Gao, Bo; Sun, Jiaren; Chen, Laiguo

    2016-11-01

    The quantile regression (QR) method has been increasingly introduced to atmospheric environmental studies to explore the non-linear relationship between local meteorological conditions and ozone mixing ratios. In this study, we applied QR for the first time, together with multiple linear regression (MLR), to analyze the dominant meteorological parameters influencing the mean, 10th percentile, 90th percentile and 99th percentile of maximum daily 8-h average (MDA8) ozone concentrations in 2000-2015 in Hong Kong. The dominance analysis (DA) was used to assess the relative importance of meteorological variables in the regression models. Results showed that the MLR models worked better at suburban and rural sites than at urban sites, and worked better in winter than in summer. QR models performed better in summer for 99th and 90th percentiles and performed better in autumn and winter for 10th percentile. And QR models also performed better in suburban and rural areas for 10th percentile. The top 3 dominant variables associated with MDA8 ozone concentrations, changing with seasons and regions, were frequently associated with the six meteorological parameters: boundary layer height, humidity, wind direction, surface solar radiation, total cloud cover and sea level pressure. Temperature rarely became a significant variable in any season, which could partly explain the peak of monthly average ozone concentrations in October in Hong Kong. And we found the effect of solar radiation would be enhanced during extremely ozone pollution episodes (i.e., the 99th percentile). Finally, meteorological effects on MDA8 ozone had no significant changes before and after the 2010 Asian Games.

  16. Seleção de variáveis em QSAR Variable selection in QSAR

    Directory of Open Access Journals (Sweden)

    Márcia Miguel Castro Ferreira

    2002-05-01

    Full Text Available The process of building mathematical models in quantitative structure-activity relationship (QSAR studies is generally limited by the size of the dataset used to select variables from. For huge datasets, the task of selecting a given number of variables that produces the best linear model can be enormous, if not unfeasible. In this case, some methods can be used to separate good parameter combinations from the bad ones. In this paper three methodologies are analyzed: systematic search, genetic algorithm and chemometric methods. These methods have been exposed and discussed through practical examples.

  17. Using exogenous variables in testing for monotonic trends in hydrologic time series

    Science.gov (United States)

    Alley, William M.

    1988-01-01

    One approach that has been used in performing a nonparametric test for monotonic trend in a hydrologic time series consists of a two-stage analysis. First, a regression equation is estimated for the variable being tested as a function of an exogenous variable. A nonparametric trend test such as the Kendall test is then performed on the residuals from the equation. By analogy to stagewise regression and through Monte Carlo experiments, it is demonstrated that this approach will tend to underestimate the magnitude of the trend and to result in some loss in power as a result of ignoring the interaction between the exogenous variable and time. An alternative approach, referred to as the adjusted variable Kendall test, is demonstrated to generally have increased statistical power and to provide more reliable estimates of the trend slope. In addition, the utility of including an exogenous variable in a trend test is examined under selected conditions.

  18. Modeling Pan Evaporation for Kuwait by Multiple Linear Regression

    Science.gov (United States)

    Almedeij, Jaber

    2012-01-01

    Evaporation is an important parameter for many projects related to hydrology and water resources systems. This paper constitutes the first study conducted in Kuwait to obtain empirical relations for the estimation of daily and monthly pan evaporation as functions of available meteorological data of temperature, relative humidity, and wind speed. The data used here for the modeling are daily measurements of substantial continuity coverage, within a period of 17 years between January 1993 and December 2009, which can be considered representative of the desert climate of the urban zone of the country. Multiple linear regression technique is used with a procedure of variable selection for fitting the best model forms. The correlations of evaporation with temperature and relative humidity are also transformed in order to linearize the existing curvilinear patterns of the data by using power and exponential functions, respectively. The evaporation models suggested with the best variable combinations were shown to produce results that are in a reasonable agreement with observation values. PMID:23226984

  19. [Prediction model of health workforce and beds in county hospitals of Hunan by multiple linear regression].

    Science.gov (United States)

    Ling, Ru; Liu, Jiawang

    2011-12-01

    To construct prediction model for health workforce and hospital beds in county hospitals of Hunan by multiple linear regression. We surveyed 16 counties in Hunan with stratified random sampling according to uniform questionnaires,and multiple linear regression analysis with 20 quotas selected by literature view was done. Independent variables in the multiple linear regression model on medical personnels in county hospitals included the counties' urban residents' income, crude death rate, medical beds, business occupancy, professional equipment value, the number of devices valued above 10 000 yuan, fixed assets, long-term debt, medical income, medical expenses, outpatient and emergency visits, hospital visits, actual available bed days, and utilization rate of hospital beds. Independent variables in the multiple linear regression model on county hospital beds included the the population of aged 65 and above in the counties, disposable income of urban residents, medical personnel of medical institutions in county area, business occupancy, the total value of professional equipment, fixed assets, long-term debt, medical income, medical expenses, outpatient and emergency visits, hospital visits, actual available bed days, utilization rate of hospital beds, and length of hospitalization. The prediction model shows good explanatory and fitting, and may be used for short- and mid-term forecasting.

  20. Multivariate sparse group lasso for the multivariate multiple linear regression with an arbitrary group structure.

    Science.gov (United States)

    Li, Yanming; Nan, Bin; Zhu, Ji

    2015-06-01

    We propose a multivariate sparse group lasso variable selection and estimation method for data with high-dimensional predictors as well as high-dimensional response variables. The method is carried out through a penalized multivariate multiple linear regression model with an arbitrary group structure for the regression coefficient matrix. It suits many biology studies well in detecting associations between multiple traits and multiple predictors, with each trait and each predictor embedded in some biological functional groups such as genes, pathways or brain regions. The method is able to effectively remove unimportant groups as well as unimportant individual coefficients within important groups, particularly for large p small n problems, and is flexible in handling various complex group structures such as overlapping or nested or multilevel hierarchical structures. The method is evaluated through extensive simulations with comparisons to the conventional lasso and group lasso methods, and is applied to an eQTL association study. © 2015, The International Biometric Society.

  1. Stagewise pseudo-value regression for time-varying effects on the cumulative incidence

    DEFF Research Database (Denmark)

    Zöller, Daniela; Schmidtmann, Irene; Weinmann, Arndt

    2016-01-01

    In a competing risks setting, the cumulative incidence of an event of interest describes the absolute risk for this event as a function of time. For regression analysis, one can either choose to model all competing events by separate cause-specific hazard models or directly model the association...... for time-varying effects. This is implemented by coupling variable selection between the grid times, but determining estimates separately. The effect estimates are regularized to also allow for model fitting with a low to moderate number of observations. This technique is illustrated in an application...

  2. Semisupervised Clustering by Iterative Partition and Regression with Neuroscience Applications

    Directory of Open Access Journals (Sweden)

    Guoqi Qian

    2016-01-01

    Full Text Available Regression clustering is a mixture of unsupervised and supervised statistical learning and data mining method which is found in a wide range of applications including artificial intelligence and neuroscience. It performs unsupervised learning when it clusters the data according to their respective unobserved regression hyperplanes. The method also performs supervised learning when it fits regression hyperplanes to the corresponding data clusters. Applying regression clustering in practice requires means of determining the underlying number of clusters in the data, finding the cluster label of each data point, and estimating the regression coefficients of the model. In this paper, we review the estimation and selection issues in regression clustering with regard to the least squares and robust statistical methods. We also provide a model selection based technique to determine the number of regression clusters underlying the data. We further develop a computing procedure for regression clustering estimation and selection. Finally, simulation studies are presented for assessing the procedure, together with analyzing a real data set on RGB cell marking in neuroscience to illustrate and interpret the method.

  3. Combining multiple regression and principal component analysis for accurate predictions for column ozone in Peninsular Malaysia

    Science.gov (United States)

    Rajab, Jasim M.; MatJafri, M. Z.; Lim, H. S.

    2013-06-01

    This study encompasses columnar ozone modelling in the peninsular Malaysia. Data of eight atmospheric parameters [air surface temperature (AST), carbon monoxide (CO), methane (CH4), water vapour (H2Ovapour), skin surface temperature (SSKT), atmosphere temperature (AT), relative humidity (RH), and mean surface pressure (MSP)] data set, retrieved from NASA's Atmospheric Infrared Sounder (AIRS), for the entire period (2003-2008) was employed to develop models to predict the value of columnar ozone (O3) in study area. The combined method, which is based on using both multiple regressions combined with principal component analysis (PCA) modelling, was used to predict columnar ozone. This combined approach was utilized to improve the prediction accuracy of columnar ozone. Separate analysis was carried out for north east monsoon (NEM) and south west monsoon (SWM) seasons. The O3 was negatively correlated with CH4, H2Ovapour, RH, and MSP, whereas it was positively correlated with CO, AST, SSKT, and AT during both the NEM and SWM season periods. Multiple regression analysis was used to fit the columnar ozone data using the atmospheric parameter's variables as predictors. A variable selection method based on high loading of varimax rotated principal components was used to acquire subsets of the predictor variables to be comprised in the linear regression model of the atmospheric parameter's variables. It was found that the increase in columnar O3 value is associated with an increase in the values of AST, SSKT, AT, and CO and with a drop in the levels of CH4, H2Ovapour, RH, and MSP. The result of fitting the best models for the columnar O3 value using eight of the independent variables gave about the same values of the R (≈0.93) and R2 (≈0.86) for both the NEM and SWM seasons. The common variables that appeared in both regression equations were SSKT, CH4 and RH, and the principal precursor of the columnar O3 value in both the NEM and SWM seasons was SSKT.

  4. Selection of controlled variables in bioprocesses. Application to a SHARON-Anammox process for autotrophic nitrogen removal

    DEFF Research Database (Denmark)

    Mauricio Iglesias, Miguel; Valverde Perez, Borja; Sin, Gürkan

    Selecting the right controlled variables in a bioprocess is challenging since the objectives of the process (yields, product or substrate concentration) are difficult to relate with a given actuator. We apply here process control tools that can be used to assist in the selection of controlled var...... variables to the case of the SHARON-Anammox process for autotrophic nitrogen removal....

  5. Establishment of regression dependences. Linear and nonlinear dependences

    International Nuclear Information System (INIS)

    Onishchenko, A.M.

    1994-01-01

    The main problems of determination of linear and 19 types of nonlinear regression dependences are completely discussed. It is taken into consideration that total dispersions are the sum of measurement dispersions and parameter variation dispersions themselves. Approaches to all dispersions determination are described. It is shown that the least square fit gives inconsistent estimation for industrial objects and processes. The correction methods by taking into account comparable measurement errors for both variable give an opportunity to obtain consistent estimation for the regression equation parameters. The condition of the correction technique application expediency is given. The technique for determination of nonlinear regression dependences taking into account the dependence form and comparable errors of both variables is described. 6 refs., 1 tab

  6. Boosted structured additive regression for Escherichia coli fed-batch fermentation modeling.

    Science.gov (United States)

    Melcher, Michael; Scharl, Theresa; Luchner, Markus; Striedner, Gerald; Leisch, Friedrich

    2017-02-01

    The quality of biopharmaceuticals and patients' safety are of highest priority and there are tremendous efforts to replace empirical production process designs by knowledge-based approaches. Main challenge in this context is that real-time access to process variables related to product quality and quantity is severely limited. To date comprehensive on- and offline monitoring platforms are used to generate process data sets that allow for development of mechanistic and/or data driven models for real-time prediction of these important quantities. Ultimate goal is to implement model based feed-back control loops that facilitate online control of product quality. In this contribution, we explore structured additive regression (STAR) models in combination with boosting as a variable selection tool for modeling the cell dry mass, product concentration, and optical density on the basis of online available process variables and two-dimensional fluorescence spectroscopic data. STAR models are powerful extensions of linear models allowing for inclusion of smooth effects or interactions between predictors. Boosting constructs the final model in a stepwise manner and provides a variable importance measure via predictor selection frequencies. Our results show that the cell dry mass can be modeled with a relative error of about ±3%, the optical density with ±6%, the soluble protein with ±16%, and the insoluble product with an accuracy of ±12%. Biotechnol. Bioeng. 2017;114: 321-334. © 2016 Wiley Periodicals, Inc. © 2016 Wiley Periodicals, Inc.

  7. Subset Selection by Local Convex Approximation

    DEFF Research Database (Denmark)

    Øjelund, Henrik; Sadegh, Payman; Madsen, Henrik

    1999-01-01

    This paper concerns selection of the optimal subset of variables in a lenear regression setting. The posed problem is combinatiorial and the globally best subset can only be found in exponential time. We define a cost function for the subset selection problem by adding the penalty term to the usual...... of the subset selection problem so as to guarantee positive definiteness of the Hessian term, hence avoiding numerical instability. The backward Elemination type algorithm attempts to improve the results upon termination of the modified Newton-Raphson search by sing the current solution as an initial guess...

  8. Predicting Social Trust with Binary Logistic Regression

    Science.gov (United States)

    Adwere-Boamah, Joseph; Hufstedler, Shirley

    2015-01-01

    This study used binary logistic regression to predict social trust with five demographic variables from a national sample of adult individuals who participated in The General Social Survey (GSS) in 2012. The five predictor variables were respondents' highest degree earned, race, sex, general happiness and the importance of personally assisting…

  9. General Nature of Multicollinearity in Multiple Regression Analysis.

    Science.gov (United States)

    Liu, Richard

    1981-01-01

    Discusses multiple regression, a very popular statistical technique in the field of education. One of the basic assumptions in regression analysis requires that independent variables in the equation should not be highly correlated. The problem of multicollinearity and some of the solutions to it are discussed. (Author)

  10. Improved variable reduction in partial least squares modelling by Global-Minimum Error Uninformative-Variable Elimination.

    Science.gov (United States)

    Andries, Jan P M; Vander Heyden, Yvan; Buydens, Lutgarde M C

    2017-08-22

    The calibration performance of Partial Least Squares regression (PLS) can be improved by eliminating uninformative variables. For PLS, many variable elimination methods have been developed. One is the Uninformative-Variable Elimination for PLS (UVE-PLS). However, the number of variables retained by UVE-PLS is usually still large. In UVE-PLS, variable elimination is repeated as long as the root mean squared error of cross validation (RMSECV) is decreasing. The set of variables in this first local minimum is retained. In this paper, a modification of UVE-PLS is proposed and investigated, in which UVE is repeated until no further reduction in variables is possible, followed by a search for the global RMSECV minimum. The method is called Global-Minimum Error Uninformative-Variable Elimination for PLS, denoted as GME-UVE-PLS or simply GME-UVE. After each iteration, the predictive ability of the PLS model, built with the remaining variable set, is assessed by RMSECV. The variable set with the global RMSECV minimum is then finally selected. The goal is to obtain smaller sets of variables with similar or improved predictability than those from the classical UVE-PLS method. The performance of the GME-UVE-PLS method is investigated using four data sets, i.e. a simulated set, NIR and NMR spectra, and a theoretical molecular descriptors set, resulting in twelve profile-response (X-y) calibrations. The selective and predictive performances of the models resulting from GME-UVE-PLS are statistically compared to those from UVE-PLS and 1-step UVE, one-sided paired t-tests. The results demonstrate that variable reduction with the proposed GME-UVE-PLS method, usually eliminates significantly more variables than the classical UVE-PLS, while the predictive abilities of the resulting models are better. With GME-UVE-PLS, a lower number of uninformative variables, without a chemical meaning for the response, may be retained than with UVE-PLS. The selectivity of the classical UVE method

  11. Modeling temporal and spatial variability of traffic-related air pollution: Hourly land use regression models for black carbon

    Science.gov (United States)

    Dons, Evi; Van Poppel, Martine; Kochan, Bruno; Wets, Geert; Int Panis, Luc

    2013-08-01

    Land use regression (LUR) modeling is a statistical technique used to determine exposure to air pollutants in epidemiological studies. Time-activity diaries can be combined with LUR models, enabling detailed exposure estimation and limiting exposure misclassification, both in shorter and longer time lags. In this study, the traffic related air pollutant black carbon was measured with μ-aethalometers on a 5-min time base at 63 locations in Flanders, Belgium. The measurements show that hourly concentrations vary between different locations, but also over the day. Furthermore the diurnal pattern is different for street and background locations. This suggests that annual LUR models are not sufficient to capture all the variation. Hourly LUR models for black carbon are developed using different strategies: by means of dummy variables, with dynamic dependent variables and/or with dynamic and static independent variables. The LUR model with 48 dummies (weekday hours and weekend hours) performs not as good as the annual model (explained variance of 0.44 compared to 0.77 in the annual model). The dataset with hourly concentrations of black carbon can be used to recalibrate the annual model, resulting in many of the original explaining variables losing their statistical significance, and certain variables having the wrong direction of effect. Building new independent hourly models, with static or dynamic covariates, is proposed as the best solution to solve these issues. R2 values for hourly LUR models are mostly smaller than the R2 of the annual model, ranging from 0.07 to 0.8. Between 6 a.m. and 10 p.m. on weekdays the R2 approximates the annual model R2. Even though models of consecutive hours are developed independently, similar variables turn out to be significant. Using dynamic covariates instead of static covariates, i.e. hourly traffic intensities and hourly population densities, did not significantly improve the models' performance.

  12. Not accounting for interindividual variability can mask habitat selection patterns: a case study on black bears.

    Science.gov (United States)

    Lesmerises, Rémi; St-Laurent, Martin-Hugues

    2017-11-01

    Habitat selection studies conducted at the population scale commonly aim to describe general patterns that could improve our understanding of the limiting factors in species-habitat relationships. Researchers often consider interindividual variation in selection patterns to control for its effects and avoid pseudoreplication by using mixed-effect models that include individuals as random factors. Here, we highlight common pitfalls and possible misinterpretations of this strategy by describing habitat selection of 21 black bears Ursus americanus. We used Bayesian mixed-effect models and compared results obtained when using random intercept (i.e., population level) versus calculating individual coefficients for each independent variable (i.e., individual level). We then related interindividual variability to individual characteristics (i.e., age, sex, reproductive status, body condition) in a multivariate analysis. The assumption of comparable behavior among individuals was verified only in 40% of the cases in our seasonal best models. Indeed, we found strong and opposite responses among sampled bears and individual coefficients were linked to individual characteristics. For some covariates, contrasted responses canceled each other out at the population level. In other cases, interindividual variability was concealed by the composition of our sample, with the majority of the bears (e.g., old individuals and bears in good physical condition) driving the population response (e.g., selection of young forest cuts). Our results stress the need to consider interindividual variability to avoid misinterpretation and uninformative results, especially for a flexible and opportunistic species. This study helps to identify some ecological drivers of interindividual variability in bear habitat selection patterns.

  13. HEART RATE VARIABILITY CLASSIFICATION USING SADE-ELM CLASSIFIER WITH BAT FEATURE SELECTION

    Directory of Open Access Journals (Sweden)

    R Kavitha

    2017-07-01

    Full Text Available The electrical activity of the human heart is measured by the vital bio medical signal called ECG. This electrocardiogram is employed as a crucial source to gather the diagnostic information of a patient’s cardiopathy. The monitoring function of cardiac disease is diagnosed by documenting and handling the electrocardiogram (ECG impulses. In the recent years many research has been done and developing an enhanced method to identify the risk in the patient’s body condition by processing and analysing the ECG signal. This analysis of the signal helps to find the cardiac abnormalities, arrhythmias, and many other heart problems. ECG signal is processed to detect the variability in heart rhythm; heart rate variability is calculated based on the time interval between heart beats. Heart Rate Variability HRV is measured by the variation in the beat to beat interval. The Heart rate Variability (HRV is an essential aspect to diagnose the properties of the heart. Recent development enhances the potential with the aid of non-linear metrics in reference point with feature selection. In this paper, the fundamental elements are taken from the ECG signal for feature selection process where Bat algorithm is employed for feature selection to predict the best feature and presented to the classifier for accurate classification. The popular machine learning algorithm ELM is taken for classification, integrated with evolutionary algorithm named Self- Adaptive Differential Evolution Extreme Learning Machine SADEELM to improve the reliability of classification. It combines Effective Fuzzy Kohonen clustering network (EFKCN to be able to increase the accuracy of the effect for HRV transmission classification. Hence, it is observed that the experiment carried out unveils that the precision is improved by the SADE-ELM method and concurrently optimizes the computation time.

  14. ASSOCIATION BETWEEN EMOTIONAL VARIABLES AND SCHOOL ACHIEVEMENT

    Directory of Open Access Journals (Sweden)

    Christoph Randler

    2009-07-01

    Full Text Available Recent psychological studies highlight emotional aspects, and they show an important role within individual learning processes. Hereby, positive emotions were supposed to positively influence learning and achievement processes and negative ones do the contrary. In this study, an educational unit “ecosystem lake” was used during which achievement (three tests and emotional variables (interest, well-being, anxiety and boredom; measured at the end of three pre-selected lessons were monitored. The research question was to explore correlations between emotional variables and the learning outcome of the teaching unit. Prior knowledge was regressed against the subsequent tests to account for its confounding effect. Regressions showed a highly significant influence of prior knowledge on the subsequent measurements of achievement. However, after accounting for prior knowledge, a positive correlation between interest/well-being and achievement and a negative correlation between anxiety/boredom and achievement was found. Further research and interventions should try to enhance positive emotions in biology lessons to positively influence achievement.

  15. Resiliency and subjective health assessment. Moderating role of selected psychosocial variables

    Directory of Open Access Journals (Sweden)

    Michalina Sołtys

    2015-12-01

    Full Text Available Background Resiliency is defined as a relatively permanent personality trait, which may be assigned to the category of health resources. The aim of this study was to determine conditions in which resiliency poses a significant health resource (moderation, thereby broadening knowledge of the specifics of the relationship between resiliency and subjective health assessment. Participants and procedure The study included 142 individuals. In order to examine the level of resiliency, the Assessment Resiliency Scale (SPP-25 by N. Ogińska-Bulik and Z. Juczyński was used. Participants evaluated subjective health state by means of an analogue-visual scale. Additionally, in the research the following moderating variables were controlled: sex, objective health status, having a partner, professional activity and age. These data were obtained by personal survey. Results The results confirmed the relationship between resiliency and subjective health assessment. Multiple regression analysis revealed that sex, having a partner and professional activity are significant moderators of associations between level of resiliency and subjective health evaluation. However, statistically significant interaction effects for health status and age as a moderator were not observed. Conclusions Resiliency is associated with subjective health assessment among adults, and selected socio-demographic features (such as sex, having a partner, professional activity moderate this relationship. This confirms the significant role of resiliency as a health resource and a reason to emphasize the benefits of enhancing the potential of individuals for their psychophysical wellbeing. However, the research requires replication in a more homogeneous sample.

  16. [Application of characteristic NIR variables selection in portable detection of soluble solids content of apple by near infrared spectroscopy].

    Science.gov (United States)

    Fan, Shu-Xiang; Huang, Wen-Qian; Li, Jiang-Bo; Guo, Zhi-Ming; Zhaq, Chun-Jiang

    2014-10-01

    In order to detect the soluble solids content(SSC)of apple conveniently and rapidly, a ring fiber probe and a portable spectrometer were applied to obtain the spectroscopy of apple. Different wavelength variable selection methods, including unin- formative variable elimination (UVE), competitive adaptive reweighted sampling (CARS) and genetic algorithm (GA) were pro- posed to select effective wavelength variables of the NIR spectroscopy of the SSC in apple based on PLS. The back interval LS- SVM (BiLS-SVM) and GA were used to select effective wavelength variables based on LS-SVM. Selected wavelength variables and full wavelength range were set as input variables of PLS model and LS-SVM model, respectively. The results indicated that PLS model built using GA-CARS on 50 characteristic variables selected from full-spectrum which had 1512 wavelengths achieved the optimal performance. The correlation coefficient (Rp) and root mean square error of prediction (RMSEP) for prediction sets were 0.962, 0.403°Brix respectively for SSC. The proposed method of GA-CARS could effectively simplify the portable detection model of SSC in apple based on near infrared spectroscopy and enhance the predictive precision. The study can provide a reference for the development of portable apple soluble solids content spectrometer.

  17. Modeling Fire Occurrence at the City Scale: A Comparison between Geographically Weighted Regression and Global Linear Regression.

    Science.gov (United States)

    Song, Chao; Kwan, Mei-Po; Zhu, Jiping

    2017-04-08

    An increasing number of fires are occurring with the rapid development of cities, resulting in increased risk for human beings and the environment. This study compares geographically weighted regression-based models, including geographically weighted regression (GWR) and geographically and temporally weighted regression (GTWR), which integrates spatial and temporal effects and global linear regression models (LM) for modeling fire risk at the city scale. The results show that the road density and the spatial distribution of enterprises have the strongest influences on fire risk, which implies that we should focus on areas where roads and enterprises are densely clustered. In addition, locations with a large number of enterprises have fewer fire ignition records, probably because of strict management and prevention measures. A changing number of significant variables across space indicate that heterogeneity mainly exists in the northern and eastern rural and suburban areas of Hefei city, where human-related facilities or road construction are only clustered in the city sub-centers. GTWR can capture small changes in the spatiotemporal heterogeneity of the variables while GWR and LM cannot. An approach that integrates space and time enables us to better understand the dynamic changes in fire risk. Thus governments can use the results to manage fire safety at the city scale.

  18. Asymptotics of Multivariate Regression with Consecutively Added Dependent Varibles

    NARCIS (Netherlands)

    Raats, V.M.; van der Genugten, B.B.; Moors, J.J.A.

    2004-01-01

    We consider multivariate regression where new dependent variables are consecutively added during the experiment (or in time).So, viewed at the end of the experiment, the number of observations decreases with each added variable. The explanatory variables are observed throughout.In a previous paper

  19. Comparison of partial least squares and lasso regression techniques as applied to laser-induced breakdown spectroscopy of geological samples

    Energy Technology Data Exchange (ETDEWEB)

    Dyar, M.D., E-mail: mdyar@mtholyoke.edu [Dept. of Astronomy, Mount Holyoke College, 50 College St., South Hadley, MA 01075 (United States); Carmosino, M.L.; Breves, E.A.; Ozanne, M.V. [Dept. of Astronomy, Mount Holyoke College, 50 College St., South Hadley, MA 01075 (United States); Clegg, S.M.; Wiens, R.C. [Los Alamos National Laboratory, P.O. Box 1663, MS J565, Los Alamos, NM 87545 (United States)

    2012-04-15

    A remote laser-induced breakdown spectrometer (LIBS) designed to simulate the ChemCam instrument on the Mars Science Laboratory Rover Curiosity was used to probe 100 geologic samples at a 9-m standoff distance. ChemCam consists of an integrated remote LIBS instrument that will probe samples up to 7 m from the mast of the rover and a remote micro-imager (RMI) that will record context images. The elemental compositions of 100 igneous and highly-metamorphosed rocks are determined with LIBS using three variations of multivariate analysis, with a goal of improving the analytical accuracy. Two forms of partial least squares (PLS) regression are employed with finely-tuned parameters: PLS-1 regresses a single response variable (elemental concentration) against the observation variables (spectra, or intensity at each of 6144 spectrometer channels), while PLS-2 simultaneously regresses multiple response variables (concentrations of the ten major elements in rocks) against the observation predictor variables, taking advantage of natural correlations between elements. Those results are contrasted with those from the multivariate regression technique of the least absolute shrinkage and selection operator (lasso), which is a penalized shrunken regression method that selects the specific channels for each element that explain the most variance in the concentration of that element. To make this comparison, we use results of cross-validation and of held-out testing, and employ unscaled and uncentered spectral intensity data because all of the input variables are already in the same units. Results demonstrate that the lasso, PLS-1, and PLS-2 all yield comparable results in terms of accuracy for this dataset. However, the interpretability of these methods differs greatly in terms of fundamental understanding of LIBS emissions. PLS techniques generate principal components, linear combinations of intensities at any number of spectrometer channels, which explain as much variance in the

  20. Regression modeling of ground-water flow

    Science.gov (United States)

    Cooley, R.L.; Naff, R.L.

    1985-01-01

    Nonlinear multiple regression methods are developed to model and analyze groundwater flow systems. Complete descriptions of regression methodology as applied to groundwater flow models allow scientists and engineers engaged in flow modeling to apply the methods to a wide range of problems. Organization of the text proceeds from an introduction that discusses the general topic of groundwater flow modeling, to a review of basic statistics necessary to properly apply regression techniques, and then to the main topic: exposition and use of linear and nonlinear regression to model groundwater flow. Statistical procedures are given to analyze and use the regression models. A number of exercises and answers are included to exercise the student on nearly all the methods that are presented for modeling and statistical analysis. Three computer programs implement the more complex methods. These three are a general two-dimensional, steady-state regression model for flow in an anisotropic, heterogeneous porous medium, a program to calculate a measure of model nonlinearity with respect to the regression parameters, and a program to analyze model errors in computed dependent variables such as hydraulic head. (USGS)

  1. Censored Hurdle Negative Binomial Regression (Case Study: Neonatorum Tetanus Case in Indonesia)

    Science.gov (United States)

    Yuli Rusdiana, Riza; Zain, Ismaini; Wulan Purnami, Santi

    2017-06-01

    Hurdle negative binomial model regression is a method that can be used for discreate dependent variable, excess zero and under- and overdispersion. It uses two parts approach. The first part estimates zero elements from dependent variable is zero hurdle model and the second part estimates not zero elements (non-negative integer) from dependent variable is called truncated negative binomial models. The discrete dependent variable in such cases is censored for some values. The type of censor that will be studied in this research is right censored. This study aims to obtain the parameter estimator hurdle negative binomial regression for right censored dependent variable. In the assessment of parameter estimation methods used Maximum Likelihood Estimator (MLE). Hurdle negative binomial model regression for right censored dependent variable is applied on the number of neonatorum tetanus cases in Indonesia. The type data is count data which contains zero values in some observations and other variety value. This study also aims to obtain the parameter estimator and test statistic censored hurdle negative binomial model. Based on the regression results, the factors that influence neonatorum tetanus case in Indonesia is the percentage of baby health care coverage and neonatal visits.

  2. Using Logistic Regression to Predict the Probability of Debris Flows in Areas Burned by Wildfires, Southern California, 2003-2006

    Science.gov (United States)

    Rupert, Michael G.; Cannon, Susan H.; Gartner, Joseph E.; Michael, John A.; Helsel, Dennis R.

    2008-01-01

    Logistic regression was used to develop statistical models that can be used to predict the probability of debris flows in areas recently burned by wildfires by using data from 14 wildfires that burned in southern California during 2003-2006. Twenty-eight independent variables describing the basin morphology, burn severity, rainfall, and soil properties of 306 drainage basins located within those burned areas were evaluated. The models were developed as follows: (1) Basins that did and did not produce debris flows soon after the 2003 to 2006 fires were delineated from data in the National Elevation Dataset using a geographic information system; (2) Data describing the basin morphology, burn severity, rainfall, and soil properties were compiled for each basin. These data were then input to a statistics software package for analysis using logistic regression; and (3) Relations between the occurrence or absence of debris flows and the basin morphology, burn severity, rainfall, and soil properties were evaluated, and five multivariate logistic regression models were constructed. All possible combinations of independent variables were evaluated to determine which combinations produced the most effective models, and the multivariate models that best predicted the occurrence of debris flows were identified. Percentage of high burn severity and 3-hour peak rainfall intensity were significant variables in all models. Soil organic matter content and soil clay content were significant variables in all models except Model 5. Soil slope was a significant variable in all models except Model 4. The most suitable model can be selected from these five models on the basis of the availability of independent variables in the particular area of interest and field checking of probability maps. The multivariate logistic regression models can be entered into a geographic information system, and maps showing the probability of debris flows can be constructed in recently burned areas of

  3. Background stratified Poisson regression analysis of cohort data.

    Science.gov (United States)

    Richardson, David B; Langholz, Bryan

    2012-03-01

    Background stratified Poisson regression is an approach that has been used in the analysis of data derived from a variety of epidemiologically important studies of radiation-exposed populations, including uranium miners, nuclear industry workers, and atomic bomb survivors. We describe a novel approach to fit Poisson regression models that adjust for a set of covariates through background stratification while directly estimating the radiation-disease association of primary interest. The approach makes use of an expression for the Poisson likelihood that treats the coefficients for stratum-specific indicator variables as 'nuisance' variables and avoids the need to explicitly estimate the coefficients for these stratum-specific parameters. Log-linear models, as well as other general relative rate models, are accommodated. This approach is illustrated using data from the Life Span Study of Japanese atomic bomb survivors and data from a study of underground uranium miners. The point estimate and confidence interval obtained from this 'conditional' regression approach are identical to the values obtained using unconditional Poisson regression with model terms for each background stratum. Moreover, it is shown that the proposed approach allows estimation of background stratified Poisson regression models of non-standard form, such as models that parameterize latency effects, as well as regression models in which the number of strata is large, thereby overcoming the limitations of previously available statistical software for fitting background stratified Poisson regression models.

  4. Multiple regression for physiological data analysis: the problem of multicollinearity.

    Science.gov (United States)

    Slinker, B K; Glantz, S A

    1985-07-01

    Multiple linear regression, in which several predictor variables are related to a response variable, is a powerful statistical tool for gaining quantitative insight into complex in vivo physiological systems. For these insights to be correct, all predictor variables must be uncorrelated. However, in many physiological experiments the predictor variables cannot be precisely controlled and thus change in parallel (i.e., they are highly correlated). There is a redundancy of information about the response, a situation called multicollinearity, that leads to numerical problems in estimating the parameters in regression equations; the parameters are often of incorrect magnitude or sign or have large standard errors. Although multicollinearity can be avoided with good experimental design, not all interesting physiological questions can be studied without encountering multicollinearity. In these cases various ad hoc procedures have been proposed to mitigate multicollinearity. Although many of these procedures are controversial, they can be helpful in applying multiple linear regression to some physiological problems.

  5. Instrumental Variables in the Long Run

    DEFF Research Database (Denmark)

    Casey, Gregory; Klemp, Marc Patrick Brag

    2017-01-01

    In the study of long-run economic growth, it is common to use historical or geographical variables as instruments for contemporary endogenous regressors. We study the interpretation of these conventional instrumental variable (IV) regressions in a general, yet simple, framework. Our aim...... quantitative implications for the field of long-run economic growth. We also use our framework to examine related empirical techniques. We find that two prominent regression methodologies - using gravity-based instruments for trade and including ancestry-adjusted variables in linear regression models - have...... is to estimate the long-run causal effect of changes in the endogenous explanatory variable. We find that conventional IV regressions generally cannot recover this parameter of interest. To estimate this parameter, therefore, we develop an augmented IV estimator that combines the conventional regression...

  6. Building optimal regression tree by ant colony system-genetic algorithm: Application to modeling of melting points

    Energy Technology Data Exchange (ETDEWEB)

    Hemmateenejad, Bahram, E-mail: hemmatb@sums.ac.ir [Department of Chemistry, Shiraz University, Shiraz (Iran, Islamic Republic of); Medicinal and Natural Products Chemistry Research Center, Shiraz University of Medical Sciences, Shiraz (Iran, Islamic Republic of); Shamsipur, Mojtaba [Department of Chemistry, Razi University, Kermanshah (Iran, Islamic Republic of); Zare-Shahabadi, Vali [Young Researchers Club, Mahshahr Branch, Islamic Azad University, Mahshahr (Iran, Islamic Republic of); Akhond, Morteza [Department of Chemistry, Shiraz University, Shiraz (Iran, Islamic Republic of)

    2011-10-17

    Highlights: {yields} Ant colony systems help to build optimum classification and regression trees. {yields} Using of genetic algorithm operators in ant colony systems resulted in more appropriate models. {yields} Variable selection in each terminal node of the tree gives promising results. {yields} CART-ACS-GA could model the melting point of organic materials with prediction errors lower than previous models. - Abstract: The classification and regression trees (CART) possess the advantage of being able to handle large data sets and yield readily interpretable models. A conventional method of building a regression tree is recursive partitioning, which results in a good but not optimal tree. Ant colony system (ACS), which is a meta-heuristic algorithm and derived from the observation of real ants, can be used to overcome this problem. The purpose of this study was to explore the use of CART and its combination with ACS for modeling of melting points of a large variety of chemical compounds. Genetic algorithm (GA) operators (e.g., cross averring and mutation operators) were combined with ACS algorithm to select the best solution model. In addition, at each terminal node of the resulted tree, variable selection was done by ACS-GA algorithm to build an appropriate partial least squares (PLS) model. To test the ability of the resulted tree, a set of approximately 4173 structures and their melting points were used (3000 compounds as training set and 1173 as validation set). Further, an external test set containing of 277 drugs was used to validate the prediction ability of the tree. Comparison of the results obtained from both trees showed that the tree constructed by ACS-GA algorithm performs better than that produced by recursive partitioning procedure.

  7. REGSTEP - stepwise multivariate polynomial regression with singular extensions

    International Nuclear Information System (INIS)

    Davierwalla, D.M.

    1977-09-01

    The program REGSTEP determines a polynomial approximation, in the least squares sense, to tabulated data. The polynomial may be univariate or multivariate. The computational method is that of stepwise regression. A variable is inserted into the regression basis if it is significant with respect to an appropriate F-test at a preselected risk level. In addition, should a variable already in the basis, become nonsignificant (again with respect to an appropriate F-test) after the entry of a new variable, it is expelled from the model. Thus only significant variables are retained in the model. Although written expressly to be incorporated into CORCOD, a code for predicting nuclear cross sections for given values of power, temperature, void fractions, Boron content etc. there is nothing to limit the use of REGSTEP to nuclear applications, as the examples demonstrate. A separate version has been incorporated into RSYST for the general user. (Auth.)

  8. Survival analysis II: Cox regression

    NARCIS (Netherlands)

    Stel, Vianda S.; Dekker, Friedo W.; Tripepi, Giovanni; Zoccali, Carmine; Jager, Kitty J.

    2011-01-01

    In contrast to the Kaplan-Meier method, Cox proportional hazards regression can provide an effect estimate by quantifying the difference in survival between patient groups and can adjust for confounding effects of other variables. The purpose of this article is to explain the basic concepts of the

  9. Assessing risk factors for periodontitis using regression

    Science.gov (United States)

    Lobo Pereira, J. A.; Ferreira, Maria Cristina; Oliveira, Teresa

    2013-10-01

    Multivariate statistical analysis is indispensable to assess the associations and interactions between different factors and the risk of periodontitis. Among others, regression analysis is a statistical technique widely used in healthcare to investigate and model the relationship between variables. In our work we study the impact of socio-demographic, medical and behavioral factors on periodontal health. Using regression, linear and logistic models, we can assess the relevance, as risk factors for periodontitis disease, of the following independent variables (IVs): Age, Gender, Diabetic Status, Education, Smoking status and Plaque Index. The multiple linear regression analysis model was built to evaluate the influence of IVs on mean Attachment Loss (AL). Thus, the regression coefficients along with respective p-values will be obtained as well as the respective p-values from the significance tests. The classification of a case (individual) adopted in the logistic model was the extent of the destruction of periodontal tissues defined by an Attachment Loss greater than or equal to 4 mm in 25% (AL≥4mm/≥25%) of sites surveyed. The association measures include the Odds Ratios together with the correspondent 95% confidence intervals.

  10. Multiple linear regression and regression with time series error models in forecasting PM10 concentrations in Peninsular Malaysia.

    Science.gov (United States)

    Ng, Kar Yong; Awang, Norhashidah

    2018-01-06

    Frequent haze occurrences in Malaysia have made the management of PM 10 (particulate matter with aerodynamic less than 10 μm) pollution a critical task. This requires knowledge on factors associating with PM 10 variation and good forecast of PM 10 concentrations. Hence, this paper demonstrates the prediction of 1-day-ahead daily average PM 10 concentrations based on predictor variables including meteorological parameters and gaseous pollutants. Three different models were built. They were multiple linear regression (MLR) model with lagged predictor variables (MLR1), MLR model with lagged predictor variables and PM 10 concentrations (MLR2) and regression with time series error (RTSE) model. The findings revealed that humidity, temperature, wind speed, wind direction, carbon monoxide and ozone were the main factors explaining the PM 10 variation in Peninsular Malaysia. Comparison among the three models showed that MLR2 model was on a same level with RTSE model in terms of forecasting accuracy, while MLR1 model was the worst.

  11. Regression-based season-ahead drought prediction for southern Peru conditioned on large-scale climate variables

    Science.gov (United States)

    Mortensen, Eric; Wu, Shu; Notaro, Michael; Vavrus, Stephen; Montgomery, Rob; De Piérola, José; Sánchez, Carlos; Block, Paul

    2018-01-01

    Located at a complex topographic, climatic, and hydrologic crossroads, southern Peru is a semiarid region that exhibits high spatiotemporal variability in precipitation. The economic viability of the region hinges on this water, yet southern Peru is prone to water scarcity caused by seasonal meteorological drought. Meteorological droughts in this region are often triggered during El Niño episodes; however, other large-scale climate mechanisms also play a noteworthy role in controlling the region's hydrologic cycle. An extensive season-ahead precipitation prediction model is developed to help bolster the existing capacity of stakeholders to plan for and mitigate deleterious impacts of drought. In addition to existing climate indices, large-scale climatic variables, such as sea surface temperature, are investigated to identify potential drought predictors. A principal component regression framework is applied to 11 potential predictors to produce an ensemble forecast of regional January-March precipitation totals. Model hindcasts of 51 years, compared to climatology and another model conditioned solely on an El Niño-Southern Oscillation index, achieve notable skill and perform better for several metrics, including ranked probability skill score and a hit-miss statistic. The information provided by the developed model and ancillary modeling efforts, such as extending the lead time of and spatially disaggregating precipitation predictions to the local level as well as forecasting the number of wet-dry days per rainy season, may further assist regional stakeholders and policymakers in preparing for drought.

  12. Reporting quality of multivariable logistic regression in selected Indian medical journals.

    Science.gov (United States)

    Kumar, R; Indrayan, A; Chhabra, P

    2012-01-01

    Use of multivariable logistic regression (MLR) modeling has steeply increased in the medical literature over the past few years. Testing of model assumptions and adequate reporting of MLR allow the reader to interpret results more accurately. To review the fulfillment of assumptions and reporting quality of MLR in selected Indian medical journals using established criteria. Analysis of published literature. Medknow.com publishes 68 Indian medical journals with open access. Eight of these journals had at least five articles using MLR between the years 1994 to 2008. Articles from each of these journals were evaluated according to the previously established 10-point quality criteria for reporting and to test the MLR model assumptions. SPSS 17 software and non-parametric test (Kruskal-Wallis H, Mann Whitney U, Spearman Correlation). One hundred and nine articles were finally found using MLR for analyzing the data in the selected eight journals. The number of such articles gradually increased after year 2003, but quality score remained almost similar over time. P value, odds ratio, and 95% confidence interval for coefficients in MLR was reported in 75.2% and sufficient cases (>10) per covariate of limiting sample size were reported in the 58.7% of the articles. No article reported the test for conformity of linear gradient for continuous covariates. Total score was not significantly different across the journals. However, involvement of statistician or epidemiologist as a co-author improved the average quality score significantly (P=0.014). Reporting of MLR in many Indian journals is incomplete. Only one article managed to score 8 out of 10 among 109 articles under review. All others scored less. Appropriate guidelines in instructions to authors, and pre-publication review of articles using MLR by a qualified statistician may improve quality of reporting.

  13. The role of multicollinearity in landslide susceptibility assessment by means of Binary Logistic Regression: comparison between VIF and AIC stepwise selection

    Science.gov (United States)

    Cama, Mariaelena; Cristi Nicu, Ionut; Conoscenti, Christian; Quénéhervé, Geraldine; Maerker, Michael

    2016-04-01

    Landslide susceptibility can be defined as the likelihood of a landslide occurring in a given area on the basis of local terrain conditions. In the last decades many research focused on its evaluation by means of stochastic approaches under the assumption that 'the past is the key to the future' which means that if a model is able to reproduce a known landslide spatial distribution, it will be able to predict the future locations of new (i.e. unknown) slope failures. Among the various stochastic approaches, Binary Logistic Regression (BLR) is one of the most used because it calculates the susceptibility in probabilistic terms and its results are easily interpretable from a geomorphological point of view. However, very often not much importance is given to multicollinearity assessment whose effect is that the coefficient estimates are unstable, with opposite sign and therefore difficult to interpret. Therefore, it should be evaluated every time in order to make a model whose results are geomorphologically correct. In this study the effects of multicollinearity in the predictive performance and robustness of landslide susceptibility models are analyzed. In particular, the multicollinearity is estimated by means of Variation Inflation Index (VIF) which is also used as selection criterion for the independent variables (VIF Stepwise Selection) and compared to the more commonly used AIC Stepwise Selection. The robustness of the results is evaluated through 100 replicates of the dataset. The study area selected to perform this analysis is the Moldavian Plateau where landslides are among the most frequent geomorphological processes. This area has an increasing trend of urbanization and a very high potential regarding the cultural heritage, being the place of discovery of the largest settlement belonging to the Cucuteni Culture from Eastern Europe (that led to the development of the great complex Cucuteni-Tripyllia). Therefore, identifying the areas susceptible to

  14. Neuropsychological Test Selection for Cognitive Impairment Classification: A Machine Learning Approach

    Science.gov (United States)

    Williams, Jennifer A.; Schmitter-Edgecombe, Maureen; Cook, Diane J.

    2016-01-01

    Introduction Reducing the amount of testing required to accurately detect cognitive impairment is clinically relevant. The aim of this research was to determine the fewest number of clinical measures required to accurately classify participants as healthy older adult, mild cognitive impairment (MCI) or dementia using a suite of classification techniques. Methods Two variable selection machine learning models (i.e., naive Bayes, decision tree), a logistic regression, and two participant datasets (i.e., clinical diagnosis, clinical dementia rating; CDR) were explored. Participants classified using clinical diagnosis criteria included 52 individuals with dementia, 97 with MCI, and 161 cognitively healthy older adults. Participants classified using CDR included 154 individuals CDR = 0, 93 individuals with CDR = 0.5, and 25 individuals with CDR = 1.0+. Twenty-seven demographic, psychological, and neuropsychological variables were available for variable selection. Results No significant difference was observed between naive Bayes, decision tree, and logistic regression models for classification of both clinical diagnosis and CDR datasets. Participant classification (70.0 – 99.1%), geometric mean (60.9 – 98.1%), sensitivity (44.2 – 100%), and specificity (52.7 – 100%) were generally satisfactory. Unsurprisingly, the MCI/CDR = 0.5 participant group was the most challenging to classify. Through variable selection only 2 – 9 variables were required for classification and varied between datasets in a clinically meaningful way. Conclusions The current study results reveal that machine learning techniques can accurately classifying cognitive impairment and reduce the number of measures required for diagnosis. PMID:26332171

  15. Improving breast cancer classification with mammography, supported on an appropriate variable selection analysis

    Science.gov (United States)

    Pérez, Noel; Guevara, Miguel A.; Silva, Augusto

    2013-02-01

    This work addresses the issue of variable selection within the context of breast cancer classification with mammography. A comprehensive repository of feature vectors was used including a hybrid subset gathering image-based and clinical features. It aimed to gather experimental evidence of variable selection in terms of cardinality, type and find a classification scheme that provides the best performance over the Area Under Receiver Operating Characteristics Curve (AUC) scores using the ranked features subset. We evaluated and classified a total of 300 subsets of features formed by the application of Chi-Square Discretization, Information-Gain, One-Rule and RELIEF methods in association with Feed-Forward Backpropagation Neural Network (FFBP), Support Vector Machine (SVM) and Decision Tree J48 (DTJ48) Machine Learning Algorithms (MLA) for a comparative performance evaluation based on AUC scores. A variable selection analysis was performed for Single-View Ranking and Multi-View Ranking groups of features. Features subsets representing Microcalcifications (MCs), Masses and both MCs and Masses lesions achieved AUC scores of 0.91, 0.954 and 0.934 respectively. Experimental evidence demonstrated that classification performance was improved by combining image-based and clinical features. The most important clinical and image-based features were StromaDistortion and Circularity respectively. Other less important but worth to use due to its consistency were Contrast, Perimeter, Microcalcification, Correlation and Elongation.

  16. PLS-based and regularization-based methods for the selection of relevant variables in non-targeted metabolomics data

    Directory of Open Access Journals (Sweden)

    Renata Bujak

    2016-07-01

    Full Text Available Non-targeted metabolomics constitutes a part of systems biology and aims to determine many metabolites in complex biological samples. Datasets obtained in non-targeted metabolomics studies are multivariate and high-dimensional due to the sensitivity of mass spectrometry-based detection methods as well as complexity of biological matrices. Proper selection of variables which contribute into group classification is a crucial step, especially in metabolomics studies which are focused on searching for disease biomarker candidates. In the present study, three different statistical approaches were tested using two metabolomics datasets (RH and PH study. Orthogonal projections to latent structures-discriminant analysis (OPLS-DA without and with multiple testing correction as well as least absolute shrinkage and selection operator (LASSO were tested and compared. For the RH study, OPLS-DA model built without multiple testing correction, selected 46 and 218 variables based on VIP criteria using Pareto and UV scaling, respectively. In the case of the PH study, 217 and 320 variables were selected based on VIP criteria using Pareto and UV scaling, respectively. In the RH study, OPLS-DA model built with multiple testing correction, selected 4 and 19 variables as statistically significant in terms of Pareto and UV scaling, respectively. For PH study, 14 and 18 variables were selected based on VIP criteria in terms of Pareto and UV scaling, respectively. Additionally, the concept and fundaments of the least absolute shrinkage and selection operator (LASSO with bootstrap procedure evaluating reproducibility of results, was demonstrated. In the RH and PH study, the LASSO selected 14 and 4 variables with reproducibility between 99.3% and 100%. However, apart from the popularity of PLS-DA and OPLS-DA methods in metabolomics, it should be highlighted that they do not control type I or type II error, but only arbitrarily establish a cut-off value for PLS-DA loadings

  17. Sparse supervised principal component analysis (SSPCA) for dimension reduction and variable selection

    DEFF Research Database (Denmark)

    Sharifzadeh, Sara; Ghodsi, Ali; Clemmensen, Line H.

    2017-01-01

    Principal component analysis (PCA) is one of the main unsupervised pre-processing methods for dimension reduction. When the training labels are available, it is worth using a supervised PCA strategy. In cases that both dimension reduction and variable selection are required, sparse PCA (SPCA...

  18. Regression and artificial neural network modeling for the prediction of gray leaf spot of maize.

    Science.gov (United States)

    Paul, P A; Munkvold, G P

    2005-04-01

    ABSTRACT Regression and artificial neural network (ANN) modeling approaches were combined to develop models to predict the severity of gray leaf spot of maize, caused by Cercospora zeae-maydis. In all, 329 cases consisting of environmental, cultural, and location-specific variables were collected for field plots in Iowa between 1998 and 2002. Disease severity on the ear leaf at the dough to dent plant growth stage was used as the response variable. Correlation and regression analyses were performed to select potentially useful predictor variables. Predictors from the best 9 of 80 regression models were used to develop ANN models. A random sample of 60% of the cases was used to train the networks, and 20% each for testing and validation. Model performance was evaluated based on coefficient of determination (R(2)) and mean square error (MSE) for the validation data set. The best models had R(2) ranging from 0.70 to 0.75 and MSE ranging from 174.7 to 202.8. The most useful predictor variables were hours of daily temperatures between 22 and 30 degrees C (85.50 to 230.50 h) and hours of nightly relative humidity >/=90% (122 to 330 h) for the period between growth stages V4 and V12, mean nightly temperature (65.26 to 76.56 degrees C) for the period between growth stages V12 and R2, longitude (90.08 to 95.14 degrees W), maize residue on the soil surface (0 to 100%), planting date (in day of the year; 112 to 182), and gray leaf spot resistance rating (2 to 7; based on a 1-to-9 scale, where 1 = most susceptible to 9 = most resistant).

  19. Relationship between the curve of Spee and craniofacial variables: A regression analysis.

    Science.gov (United States)

    Halimi, Abdelali; Benyahia, Hicham; Azeroual, Mohamed-Faouzi; Bahije, Loubna; Zaoui, Fatima

    2018-06-01

    The aim of this regression analysis was to identify the determining factors, which impact the curve of Spee during its genesis, its therapeutic reconstruction, and its stability, within a continuously evolving craniofacial morphology throughout life. We selected a total of 107 patients, according to the inclusion criteria. A morphological and functional clinical examination was performed for each patient: plaster models, tracing of the curve of Spee, crowding, Angle's classification, overjet and overbite were thus recorded. Then, we made a cephalometric analysis based on the standardized lateral cephalograms. In the sagittal dimension, we measured the values of angles ANB, SNA, SNB, SND, I/i; and the following distances: AoBo, I/NA, i/NB, SE and SL. In the vertical dimension, we measured the values of angles FMA, GoGn/SN, the occlusal plane, and the following distances: SAr, ArD, Ar/Con, Con/Gn, GoPo, HFP, HFA and IF. The statistical analysis was performed using the SPSS software with a significance level of 0.05. Our sample including 107 subjects was composed of 77 female patients (71.3%) and 30 male patients (27.8%) 7 hypodivergent patients (6.5%), 56 hyperdivergent patients (52.3%) and 44 normodivergent patients (41.1%). Patients' mean age was 19.35±5.95 years. The hypodivergent patients presented more pronounced curves of Spee compared to the normodivergent and the hyperdivergent populations; patients in skeletal Class I presented less pronounced curves of Spee compared to patients in skeletal Class II and Class III. These differences were non significant (P>0.05). The curve of Spee was positively and moderately correlated with Angle's classification, overjet, overbite, sellion-articulare distance, and breathing type (P0.05). Seventy five percent (75%) of the hyperdivergent patients with an oral breathing presented an overbite of 3mm, which is quite excessive given the characteristics often admitted for this typology; this parameter could explain the overbite

  20. A comparison on parameter-estimation methods in multiple regression analysis with existence of multicollinearity among independent variables

    Directory of Open Access Journals (Sweden)

    Hukharnsusatrue, A.

    2005-11-01

    Full Text Available The objective of this research is to compare multiple regression coefficients estimating methods with existence of multicollinearity among independent variables. The estimation methods are Ordinary Least Squares method (OLS, Restricted Least Squares method (RLS, Restricted Ridge Regression method (RRR and Restricted Liu method (RL when restrictions are true and restrictions are not true. The study used the Monte Carlo Simulation method. The experiment was repeated 1,000 times under each situation. The analyzed results of the data are demonstrated as follows. CASE 1: The restrictions are true. In all cases, RRR and RL methods have a smaller Average Mean Square Error (AMSE than OLS and RLS method, respectively. RRR method provides the smallest AMSE when the level of correlations is high and also provides the smallest AMSE for all level of correlations and all sample sizes when standard deviation is equal to 5. However, RL method provides the smallest AMSE when the level of correlations is low and middle, except in the case of standard deviation equal to 3, small sample sizes, RRR method provides the smallest AMSE.The AMSE varies with, most to least, respectively, level of correlations, standard deviation and number of independent variables but inversely with to sample size.CASE 2: The restrictions are not true.In all cases, RRR method provides the smallest AMSE, except in the case of standard deviation equal to 1 and error of restrictions equal to 5%, OLS method provides the smallest AMSE when the level of correlations is low or median and there is a large sample size, but the small sample sizes, RL method provides the smallest AMSE. In addition, when error of restrictions is increased, OLS method provides the smallest AMSE for all level, of correlations and all sample sizes, except when the level of correlations is high and sample sizes small. Moreover, the case OLS method provides the smallest AMSE, the most RLS method has a smaller AMSE than

  1. Kernel regression with functional response

    OpenAIRE

    Ferraty, Frédéric; Laksaci, Ali; Tadj, Amel; Vieu, Philippe

    2011-01-01

    We consider kernel regression estimate when both the response variable and the explanatory one are functional. The rates of uniform almost complete convergence are stated as function of the small ball probability of the predictor and as function of the entropy of the set on which uniformity is obtained.

  2. Modelos de regresión para variables expresadas como una proporción continua Regression models for variables expressed as a continuous proportion

    Directory of Open Access Journals (Sweden)

    Aarón Salinas-Rodríguez

    2006-10-01

    the Public Health field. MATERIAL AND METHODS: From the National Reproductive Health Survey performed in 2003, the proportion of individual coverage in the family planning program -proposed in one study carried out in the National Institute of Public Health in Cuernavaca, Morelos, Mexico (2005- was modeled using the Normal, Gamma, Beta and quasi-likelihood regression models. The Akaike Information Criterion (AIC proposed by McQuarrie and Tsai was used to define the best model. Then, using a simulation (Monte Carlo/Markov Chains approach a variable with a Beta distribution was generated to evaluate the behavior of the 4 models while varying the sample size from 100 to 18 000 observations. RESULTS: Results showed that the best statistical option for the analysis of continuous proportions was the Beta regression model, since its assumptions are easily accomplished and because it had the lowest AIC value. Simulation evidenced that while the sample size increases the Gamma, and even more so the quasi-likelihood, models come significantly close to the Beta regression model. CONCLUSIONS: The use of parametric Beta regression is highly recommended to model continuous proportions and the normal model should be avoided. If the sample size is large enough, the use of quasi-likelihood model represents a good alternative.

  3. Evaluating the performance of different predictor strategies in regression-based downscaling with a focus on glacierized mountain environments

    Science.gov (United States)

    Hofer, Marlis; Nemec, Johanna

    2016-04-01

    This study presents first steps towards verifying the hypothesis that uncertainty in global and regional glacier mass simulations can be reduced considerably by reducing the uncertainty in the high-resolution atmospheric input data. To this aim, we systematically explore the potential of different predictor strategies for improving the performance of regression-based downscaling approaches. The investigated local-scale target variables are precipitation, air temperature, wind speed, relative humidity and global radiation, all at a daily time scale. Observations of these target variables are assessed from three sites in geo-environmentally and climatologically very distinct settings, all within highly complex topography and in the close proximity to mountain glaciers: (1) the Vernagtbach station in the Northern European Alps (VERNAGT), (2) the Artesonraju measuring site in the tropical South American Andes (ARTESON), and (3) the Brewster measuring site in the Southern Alps of New Zealand (BREWSTER). As the large-scale predictors, ERA interim reanalysis data are used. In the applied downscaling model training and evaluation procedures, particular emphasis is put on appropriately accounting for the pitfalls of limited and/or patchy observation records that are usually the only (if at all) available data from the glacierized mountain sites. Generalized linear models and beta regression are investigated as alternatives to ordinary least squares regression for the non-Gaussian target variables. By analyzing results for the three different sites, five predictands and for different times of the year, we look for systematic improvements in the downscaling models' skill specifically obtained by (i) using predictor data at the optimum scale rather than the minimum scale of the reanalysis data, (ii) identifying the optimum predictor allocation in the vertical, and (iii) considering multiple (variable, level and/or grid point) predictor options combined with state

  4. On the shape of posterior densities and credible sets in instrumental variable regression models with reduced rank: an application of flexible sampling methods using neural networks

    NARCIS (Netherlands)

    Hoogerheide, L.F.; Kaashoek, J.F.; van Dijk, H.K.

    2007-01-01

    Likelihoods and posteriors of instrumental variable (IV) regression models with strong endogeneity and/or weak instruments may exhibit rather non-elliptical contours in the parameter space. This may seriously affect inference based on Bayesian credible sets. When approximating posterior

  5. Evaluation of heat transfer mathematical models and multiple linear regression to predict the inside variables in semi-solar greenhouse

    Directory of Open Access Journals (Sweden)

    M Taki

    2017-05-01

    Full Text Available Introduction Controlling greenhouse microclimate not only influences the growth of plants, but also is critical in the spread of diseases inside the greenhouse. The microclimate parameters were inside air, greenhouse roof and soil temperature, relative humidity and solar radiation intensity. Predicting the microclimate conditions inside a greenhouse and enabling the use of automatic control systems are the two main objectives of greenhouse climate model. The microclimate inside a greenhouse can be predicted by conducting experiments or by using simulation. Static and dynamic models are used for this purpose as a function of the metrological conditions and the parameters of the greenhouse components. Some works were done in past to 2015 year to simulation and predict the inside variables in different greenhouse structures. Usually simulation has a lot of problems to predict the inside climate of greenhouse and the error of simulation is higher in literature. The main objective of this paper is comparison between heat transfer and regression models to evaluate them to predict inside air and roof temperature in a semi-solar greenhouse in Tabriz University. Materials and Methods In this study, a semi-solar greenhouse was designed and constructed at the North-West of Iran in Azerbaijan Province (geographical location of 38°10′ N and 46°18′ E with elevation of 1364 m above the sea level. In this research, shape and orientation of the greenhouse, selected between some greenhouses common shapes and according to receive maximum solar radiation whole the year. Also internal thermal screen and cement north wall was used to store and prevent of heat lost during the cold period of year. So we called this structure, ‘semi-solar’ greenhouse. It was covered with glass (4 mm thickness. It occupies a surface of approximately 15.36 m2 and 26.4 m3. The orientation of this greenhouse was East–West and perpendicular to the direction of the wind prevailing

  6. Modelling fourier regression for time series data- a case study: modelling inflation in foods sector in Indonesia

    Science.gov (United States)

    Prahutama, Alan; Suparti; Wahyu Utami, Tiani

    2018-03-01

    Regression analysis is an analysis to model the relationship between response variables and predictor variables. The parametric approach to the regression model is very strict with the assumption, but nonparametric regression model isn’t need assumption of model. Time series data is the data of a variable that is observed based on a certain time, so if the time series data wanted to be modeled by regression, then we should determined the response and predictor variables first. Determination of the response variable in time series is variable in t-th (yt), while the predictor variable is a significant lag. In nonparametric regression modeling, one developing approach is to use the Fourier series approach. One of the advantages of nonparametric regression approach using Fourier series is able to overcome data having trigonometric distribution. In modeling using Fourier series needs parameter of K. To determine the number of K can be used Generalized Cross Validation method. In inflation modeling for the transportation sector, communication and financial services using Fourier series yields an optimal K of 120 parameters with R-square 99%. Whereas if it was modeled by multiple linear regression yield R-square 90%.

  7. Spatial variability of excess mortality during prolonged dust events in a high-density city: a time-stratified spatial regression approach.

    Science.gov (United States)

    Wong, Man Sing; Ho, Hung Chak; Yang, Lin; Shi, Wenzhong; Yang, Jinxin; Chan, Ta-Chien

    2017-07-24

    Dust events have long been recognized to be associated with a higher mortality risk. However, no study has investigated how prolonged dust events affect the spatial variability of mortality across districts in a downwind city. In this study, we applied a spatial regression approach to estimate the district-level mortality during two extreme dust events in Hong Kong. We compared spatial and non-spatial models to evaluate the ability of each regression to estimate mortality. We also compared prolonged dust events with non-dust events to determine the influences of community factors on mortality across the city. The density of a built environment (estimated by the sky view factor) had positive association with excess mortality in each district, while socioeconomic deprivation contributed by lower income and lower education induced higher mortality impact in each territory planning unit during a prolonged dust event. Based on the model comparison, spatial error modelling with the 1st order of queen contiguity consistently outperformed other models. The high-risk areas with higher increase in mortality were located in an urban high-density environment with higher socioeconomic deprivation. Our model design shows the ability to predict spatial variability of mortality risk during an extreme weather event that is not able to be estimated based on traditional time-series analysis or ecological studies. Our spatial protocol can be used for public health surveillance, sustainable planning and disaster preparation when relevant data are available.

  8. Current Debates on Variability in Child Welfare Decision-Making: A Selected Literature Review

    Directory of Open Access Journals (Sweden)

    Emily Keddell

    2014-11-01

    Full Text Available This article considers selected drivers of decision variability in child welfare decision-making and explores current debates in relation to these drivers. Covering the related influences of national orientation, risk and responsibility, inequality and poverty, evidence-based practice, constructions of abuse and its causes, domestic violence and cognitive processes, it discusses the literature in regards to how each of these influences decision variability. It situates these debates in relation to the ethical issue of variability and the equity issues that variability raises. I propose that despite the ecological complexity that drives decision variability, that improving internal (within-country decision consistency is still a valid goal. It may be that the use of annotated case examples, kind learning systems, and continued commitments to the social justice issues of inequality and individualisation can contribute to this goal.

  9. Regression in organizational leadership.

    Science.gov (United States)

    Kernberg, O F

    1979-02-01

    The choice of good leaders is a major task for all organizations. Inforamtion regarding the prospective administrator's personality should complement questions regarding his previous experience, his general conceptual skills, his technical knowledge, and the specific skills in the area for which he is being selected. The growing psychoanalytic knowledge about the crucial importance of internal, in contrast to external, object relations, and about the mutual relationships of regression in individuals and in groups, constitutes an important practical tool for the selection of leaders.

  10. Background stratified Poisson regression analysis of cohort data

    International Nuclear Information System (INIS)

    Richardson, David B.; Langholz, Bryan

    2012-01-01

    Background stratified Poisson regression is an approach that has been used in the analysis of data derived from a variety of epidemiologically important studies of radiation-exposed populations, including uranium miners, nuclear industry workers, and atomic bomb survivors. We describe a novel approach to fit Poisson regression models that adjust for a set of covariates through background stratification while directly estimating the radiation-disease association of primary interest. The approach makes use of an expression for the Poisson likelihood that treats the coefficients for stratum-specific indicator variables as 'nuisance' variables and avoids the need to explicitly estimate the coefficients for these stratum-specific parameters. Log-linear models, as well as other general relative rate models, are accommodated. This approach is illustrated using data from the Life Span Study of Japanese atomic bomb survivors and data from a study of underground uranium miners. The point estimate and confidence interval obtained from this 'conditional' regression approach are identical to the values obtained using unconditional Poisson regression with model terms for each background stratum. Moreover, it is shown that the proposed approach allows estimation of background stratified Poisson regression models of non-standard form, such as models that parameterize latency effects, as well as regression models in which the number of strata is large, thereby overcoming the limitations of previously available statistical software for fitting background stratified Poisson regression models. (orig.)

  11. On the shape of posterior densities and credible sets in instrumental variable regression models with reduced rank: an application of flexible sampling methods using neural networks

    NARCIS (Netherlands)

    L.F. Hoogerheide (Lennart); J.F. Kaashoek (Johan); H.K. van Dijk (Herman)

    2005-01-01

    textabstractLikelihoods and posteriors of instrumental variable regression models with strong endogeneity and/or weak instruments may exhibit rather non-elliptical contours in the parameter space. This may seriously affect inference based on Bayesian credible sets. When approximating such contours

  12. Analysis of Relationship Between Personality and Favorite Places with Poisson Regression Analysis

    Directory of Open Access Journals (Sweden)

    Yoon Song Ha

    2018-01-01

    Full Text Available A relationship between human personality and preferred locations have been a long conjecture for human mobility research. In this paper, we analyzed the relationship between personality and visiting place with Poisson Regression. Poisson Regression can analyze correlation between countable dependent variable and independent variable. For this analysis, 33 volunteers provided their personality data and 49 location categories data are used. Raw location data is preprocessed to be normalized into rates of visit and outlier data is prunned. For the regression analysis, independent variables are personality data and dependent variables are preprocessed location data. Several meaningful results are found. For example, persons with high tendency of frequent visiting to university laboratory has personality with high conscientiousness and low openness. As well, other meaningful location categories are presented in this paper.

  13. Modeling the dynamics of urban growth using multinomial logistic regression: a case study of Jiayu County, Hubei Province, China

    Science.gov (United States)

    Nong, Yu; Du, Qingyun; Wang, Kun; Miao, Lei; Zhang, Weiwei

    2008-10-01

    Urban growth modeling, one of the most important aspects of land use and land cover change study, has attracted substantial attention because it helps to comprehend the mechanisms of land use change thus helps relevant policies made. This study applied multinomial logistic regression to model urban growth in the Jiayu county of Hubei province, China to discover the relationship between urban growth and the driving forces of which biophysical and social-economic factors are selected as independent variables. This type of regression is similar to binary logistic regression, but it is more general because the dependent variable is not restricted to two categories, as those previous studies did. The multinomial one can simulate the process of multiple land use competition between urban land, bare land, cultivated land and orchard land. Taking the land use type of Urban as reference category, parameters could be estimated with odds ratio. A probability map is generated from the model to predict where urban growth will occur as a result of the computation.

  14. Poisson regression approach for modeling fatal injury rates amongst Malaysian workers

    International Nuclear Information System (INIS)

    Kamarulzaman Ibrahim; Heng Khai Theng

    2005-01-01

    Many safety studies are based on the analysis carried out on injury surveillance data. The injury surveillance data gathered for the analysis include information on number of employees at risk of injury in each of several strata where the strata are defined in terms of a series of important predictor variables. Further insight into the relationship between fatal injury rates and predictor variables may be obtained by the poisson regression approach. Poisson regression is widely used in analyzing count data. In this study, poisson regression is used to model the relationship between fatal injury rates and predictor variables which are year (1995-2002), gender, recording system and industry type. Data for the analysis were obtained from PERKESO and Jabatan Perangkaan Malaysia. It is found that the assumption that the data follow poisson distribution has been violated. After correction for the problem of over dispersion, the predictor variables that are found to be significant in the model are gender, system of recording, industry type, two interaction effects (interaction between recording system and industry type and between year and industry type). Introduction Regression analysis is one of the most popular

  15. Variations in Carabidae assemblages across the farmland habitats in relation to selected environmental variables including soil properties

    Directory of Open Access Journals (Sweden)

    Beáta Baranová

    2018-03-01

    Full Text Available The variations in ground beetles (Coleoptera: Carabidae assemblages across the three types of farmland habitats, arable land, meadows and woody vegetation were studied in relation to vegetation cover structure, intensity of agrotechnical interventions and selected soil properties. Material was pitfall trapped in 2010 and 2011 on twelve sites of the agricultural landscape in the Prešov town and its near vicinity, Eastern Slovakia. A total of 14,763 ground beetle individuals were entrapped. Material collection resulted into 92 Carabidae species, with the following six species dominating: Poecilus cupreus, Pterostichus melanarius, Pseudoophonus rufipes, Brachinus crepitans, Anchomenus dorsalis and Poecilus versicolor. Studied habitats differed significantly in the number of entrapped individuals, activity abundance as well as representation of the carabids according to their habitat preferences and ability to fly. However, no significant distinction was observed in the diversity, evenness neither dominance. The most significant environmental variables affecting Carabidae assemblages species variability were soil moisture and herb layer 0-20 cm. Another best variables selected by the forward selection were intensity of agrotechnical interventions, humus content and shrub vegetation. The other from selected soil properties seem to have just secondary meaning for the adult carabids. Environmental variables have the strongest effect on the habitat specialists, whereas ground beetles without special requirements to the habitat quality seem to be affected by the studied environmental variables just little.

  16. Logistic regression for dichotomized counts.

    Science.gov (United States)

    Preisser, John S; Das, Kalyan; Benecha, Habtamu; Stamm, John W

    2016-12-01

    Sometimes there is interest in a dichotomized outcome indicating whether a count variable is positive or zero. Under this scenario, the application of ordinary logistic regression may result in efficiency loss, which is quantifiable under an assumed model for the counts. In such situations, a shared-parameter hurdle model is investigated for more efficient estimation of regression parameters relating to overall effects of covariates on the dichotomous outcome, while handling count data with many zeroes. One model part provides a logistic regression containing marginal log odds ratio effects of primary interest, while an ancillary model part describes the mean count of a Poisson or negative binomial process in terms of nuisance regression parameters. Asymptotic efficiency of the logistic model parameter estimators of the two-part models is evaluated with respect to ordinary logistic regression. Simulations are used to assess the properties of the models with respect to power and Type I error, the latter investigated under both misspecified and correctly specified models. The methods are applied to data from a randomized clinical trial of three toothpaste formulations to prevent incident dental caries in a large population of Scottish schoolchildren. © The Author(s) 2014.

  17. Estimasi Model Seemingly Unrelated Regression (SUR dengan Metode Generalized Least Square (GLS

    Directory of Open Access Journals (Sweden)

    Ade Widyaningsih

    2015-04-01

    Full Text Available Regression analysis is a statistical tool that is used to determine the relationship between two or more quantitative variables so that one variable can be predicted from the other variables. A method that can used to obtain a good estimation in the regression analysis is ordinary least squares method. The least squares method is used to estimate the parameters of one or more regression but relationships among the errors in the response of other estimators are not allowed. One way to overcome this problem is Seemingly Unrelated Regression model (SUR in which parameters are estimated using Generalized Least Square (GLS. In this study, the author applies SUR model using GLS method on world gasoline demand data. The author obtains that SUR using GLS is better than OLS because SUR produce smaller errors than the OLS.

  18. Estimasi Model Seemingly Unrelated Regression (SUR dengan Metode Generalized Least Square (GLS

    Directory of Open Access Journals (Sweden)

    Ade Widyaningsih

    2014-06-01

    Full Text Available Regression analysis is a statistical tool that is used to determine the relationship between two or more quantitative variables so that one variable can be predicted from the other variables. A method that can used to obtain a good estimation in the regression analysis is ordinary least squares method. The least squares method is used to estimate the parameters of one or more regression but relationships among the errors in the response of other estimators are not allowed. One way to overcome this problem is Seemingly Unrelated Regression model (SUR in which parameters are estimated using Generalized Least Square (GLS. In this study, the author applies SUR model using GLS method on world gasoline demand data. The author obtains that SUR using GLS is better than OLS because SUR produce smaller errors than the OLS.

  19. A Practical pedestrian approach to parsimonious regression with inaccurate inputs

    Directory of Open Access Journals (Sweden)

    Seppo Karrila

    2014-04-01

    Full Text Available A measurement result often dictates an interval containing the correct value. Interval data is also created by roundoff, truncation, and binning. We focus on such common interval uncertainty in data. Inaccuracy in model inputs is typically ignored on model fitting. We provide a practical approach for regression with inaccurate data: the mathematics is easy, and the linear programming formulations simple to use even in a spreadsheet. This self-contained elementary presentation introduces interval linear systems and requires only basic knowledge of algebra. Feature selection is automatic; but can be controlled to find only a few most relevant inputs; and joint feature selection is enabled for multiple modeled outputs. With more features than cases, a novel connection to compressed sensing emerges: robustness against interval errors-in-variables implies model parsimony, and the input inaccuracies determine the regularization term. A small numerical example highlights counterintuitive results and a dramatic difference to total least squares.

  20. Multinomial logistic regression in workers' health

    Science.gov (United States)

    Grilo, Luís M.; Grilo, Helena L.; Gonçalves, Sónia P.; Junça, Ana

    2017-11-01

    In European countries, namely in Portugal, it is common to hear some people mentioning that they are exposed to excessive and continuous psychosocial stressors at work. This is increasing in diverse activity sectors, such as, the Services sector. A representative sample was collected from a Portuguese Services' organization, by applying a survey (internationally validated), which variables were measured in five ordered categories in Likert-type scale. A multinomial logistic regression model is used to estimate the probability of each category of the dependent variable general health perception where, among other independent variables, burnout appear as statistically significant.

  1. The Selection, Use, and Reporting of Control Variables in International Business Research

    DEFF Research Database (Denmark)

    Nielsen, Bo Bernhard; Raswant, Arpit

    2018-01-01

    This study explores the selection, use, and reporting of control variables in studies published in the leading international business (IB) research journals. We review a sample of 246 empirical studies published in the top five IB journals over the period 2012–2015 with particular emphasis...... on selection, use, and reporting of controls. Approximately 83% of studies included only half of what we consider Minimum Standard of Practice with regards to controls, whereas only 38% of the studies met the 75% threshold. We provide recommendations on how to effectively identify, use and report controls...

  2. Bayesian inference for the genetic control of water deficit tolerance in spring wheat by stochastic search variable selection.

    Science.gov (United States)

    Safari, Parviz; Danyali, Syyedeh Fatemeh; Rahimi, Mehdi

    2018-06-02

    Drought is the main abiotic stress seriously influencing wheat production. Information about the inheritance of drought tolerance is necessary to determine the most appropriate strategy to develop tolerant cultivars and populations. In this study, generation means analysis to identify the genetic effects controlling grain yield inheritance in water deficit and normal conditions was considered as a model selection problem in a Bayesian framework. Stochastic search variable selection (SSVS) was applied to identify the most important genetic effects and the best fitted models using different generations obtained from two crosses applying two water regimes in two growing seasons. The SSVS is used to evaluate the effect of each variable on the dependent variable via posterior variable inclusion probabilities. The model with the highest posterior probability is selected as the best model. In this study, the grain yield was controlled by the main effects (additive and non-additive effects) and epistatic. The results demonstrate that breeding methods such as recurrent selection and subsequent pedigree method and hybrid production can be useful to improve grain yield.

  3. ACTIVE LEARNING TO OVERCOME SAMPLE SELECTION BIAS: APPLICATION TO PHOTOMETRIC VARIABLE STAR CLASSIFICATION

    Energy Technology Data Exchange (ETDEWEB)

    Richards, Joseph W.; Starr, Dan L.; Miller, Adam A.; Bloom, Joshua S.; Butler, Nathaniel R.; Berian James, J. [Astronomy Department, University of California, Berkeley, CA 94720-7450 (United States); Brink, Henrik [Dark Cosmology Centre, Juliane Maries Vej 30, 2100 Copenhagen O (Denmark); Long, James P.; Rice, John, E-mail: jwrichar@stat.berkeley.edu [Statistics Department, University of California, Berkeley, CA 94720-7450 (United States)

    2012-01-10

    Despite the great promise of machine-learning algorithms to classify and predict astrophysical parameters for the vast numbers of astrophysical sources and transients observed in large-scale surveys, the peculiarities of the training data often manifest as strongly biased predictions on the data of interest. Typically, training sets are derived from historical surveys of brighter, more nearby objects than those from more extensive, deeper surveys (testing data). This sample selection bias can cause catastrophic errors in predictions on the testing data because (1) standard assumptions for machine-learned model selection procedures break down and (2) dense regions of testing space might be completely devoid of training data. We explore possible remedies to sample selection bias, including importance weighting, co-training, and active learning (AL). We argue that AL-where the data whose inclusion in the training set would most improve predictions on the testing set are queried for manual follow-up-is an effective approach and is appropriate for many astronomical applications. For a variable star classification problem on a well-studied set of stars from Hipparcos and Optical Gravitational Lensing Experiment, AL is the optimal method in terms of error rate on the testing data, beating the off-the-shelf classifier by 3.4% and the other proposed methods by at least 3.0%. To aid with manual labeling of variable stars, we developed a Web interface which allows for easy light curve visualization and querying of external databases. Finally, we apply AL to classify variable stars in the All Sky Automated Survey, finding dramatic improvement in our agreement with the ASAS Catalog of Variable Stars, from 65.5% to 79.5%, and a significant increase in the classifier's average confidence for the testing set, from 14.6% to 42.9%, after a few AL iterations.

  4. ACTIVE LEARNING TO OVERCOME SAMPLE SELECTION BIAS: APPLICATION TO PHOTOMETRIC VARIABLE STAR CLASSIFICATION

    International Nuclear Information System (INIS)

    Richards, Joseph W.; Starr, Dan L.; Miller, Adam A.; Bloom, Joshua S.; Butler, Nathaniel R.; Berian James, J.; Brink, Henrik; Long, James P.; Rice, John

    2012-01-01

    Despite the great promise of machine-learning algorithms to classify and predict astrophysical parameters for the vast numbers of astrophysical sources and transients observed in large-scale surveys, the peculiarities of the training data often manifest as strongly biased predictions on the data of interest. Typically, training sets are derived from historical surveys of brighter, more nearby objects than those from more extensive, deeper surveys (testing data). This sample selection bias can cause catastrophic errors in predictions on the testing data because (1) standard assumptions for machine-learned model selection procedures break down and (2) dense regions of testing space might be completely devoid of training data. We explore possible remedies to sample selection bias, including importance weighting, co-training, and active learning (AL). We argue that AL—where the data whose inclusion in the training set would most improve predictions on the testing set are queried for manual follow-up—is an effective approach and is appropriate for many astronomical applications. For a variable star classification problem on a well-studied set of stars from Hipparcos and Optical Gravitational Lensing Experiment, AL is the optimal method in terms of error rate on the testing data, beating the off-the-shelf classifier by 3.4% and the other proposed methods by at least 3.0%. To aid with manual labeling of variable stars, we developed a Web interface which allows for easy light curve visualization and querying of external databases. Finally, we apply AL to classify variable stars in the All Sky Automated Survey, finding dramatic improvement in our agreement with the ASAS Catalog of Variable Stars, from 65.5% to 79.5%, and a significant increase in the classifier's average confidence for the testing set, from 14.6% to 42.9%, after a few AL iterations.

  5. Active Learning to Overcome Sample Selection Bias: Application to Photometric Variable Star Classification

    Science.gov (United States)

    Richards, Joseph W.; Starr, Dan L.; Brink, Henrik; Miller, Adam A.; Bloom, Joshua S.; Butler, Nathaniel R.; James, J. Berian; Long, James P.; Rice, John

    2012-01-01

    Despite the great promise of machine-learning algorithms to classify and predict astrophysical parameters for the vast numbers of astrophysical sources and transients observed in large-scale surveys, the peculiarities of the training data often manifest as strongly biased predictions on the data of interest. Typically, training sets are derived from historical surveys of brighter, more nearby objects than those from more extensive, deeper surveys (testing data). This sample selection bias can cause catastrophic errors in predictions on the testing data because (1) standard assumptions for machine-learned model selection procedures break down and (2) dense regions of testing space might be completely devoid of training data. We explore possible remedies to sample selection bias, including importance weighting, co-training, and active learning (AL). We argue that AL—where the data whose inclusion in the training set would most improve predictions on the testing set are queried for manual follow-up—is an effective approach and is appropriate for many astronomical applications. For a variable star classification problem on a well-studied set of stars from Hipparcos and Optical Gravitational Lensing Experiment, AL is the optimal method in terms of error rate on the testing data, beating the off-the-shelf classifier by 3.4% and the other proposed methods by at least 3.0%. To aid with manual labeling of variable stars, we developed a Web interface which allows for easy light curve visualization and querying of external databases. Finally, we apply AL to classify variable stars in the All Sky Automated Survey, finding dramatic improvement in our agreement with the ASAS Catalog of Variable Stars, from 65.5% to 79.5%, and a significant increase in the classifier's average confidence for the testing set, from 14.6% to 42.9%, after a few AL iterations.

  6. Assessment of deforestation using regression; Hodnotenie odlesnenia s vyuzitim regresie

    Energy Technology Data Exchange (ETDEWEB)

    Juristova, J. [Univerzita Komenskeho, Prirodovedecka fakulta, Katedra kartografie, geoinformatiky a DPZ, 84215 Bratislava (Slovakia)

    2013-04-16

    This work is devoted to the evaluation of deforestation using regression methods through software Idrisi Taiga. Deforestation is evaluated by the method of logistic regression. The dependent variable has discrete values '0' and '1', indicating that the deforestation occurred or not. Independent variables have continuous values, expressing the distance from the edge of the deforested areas of forests from urban areas, the river and the road network. The results were also used in predicting the probability of deforestation in subsequent periods. The result is a map showing the output probability of deforestation for the periods 1990/2000 and 200/2006 in accordance with predetermined coefficients (values of independent variables). (authors)

  7. Generation of daily global solar irradiation with support vector machines for regression

    International Nuclear Information System (INIS)

    Antonanzas-Torres, F.; Urraca, R.; Antonanzas, J.; Fernandez-Ceniceros, J.; Martinez-de-Pison, F.J.

    2015-01-01

    Highlights: • New methodology for estimation of daily solar irradiation with SVR. • Automatic procedure for training models and selecting meteorological features. • This methodology outperforms other well-known parametric and numeric techniques. - Abstract: Solar global irradiation is barely recorded in isolated rural areas around the world. Traditionally, solar resource estimation has been performed using parametric-empirical models based on the relationship of solar irradiation with other atmospheric and commonly measured variables, such as temperatures, rainfall, and sunshine duration, achieving a relatively high level of certainty. Considerable improvement in soft-computing techniques, which have been applied extensively in many research fields, has lead to improvements in solar global irradiation modeling, although most of these techniques lack spatial generalization. This new methodology proposes support vector machines for regression with optimized variable selection via genetic algorithms to generate non-locally dependent and accurate models. A case of study in Spain has demonstrated the value of this methodology. It achieved a striking reduction in the mean absolute error (MAE) – 41.4% and 19.9% – as compared to classic parametric models; Bristow & Campbell and Antonanzas-Torres et al., respectively

  8. Pengaruh beberapa variable terhadap Pemilihan Metode Penilaian Persediaan pada Perusahaan Manufaktur

    Directory of Open Access Journals (Sweden)

    Herlin Tundjung Setijaningsih

    2009-03-01

    Full Text Available This study aims to provide empirical evidence whether the size of the company, inventory intensity, variability cost of sales, and accounting earnings variability influence the choice of inventory valuation methods. The object of this research was manufacturing companies listed in Indonesia Stock Exchange in the period 2005-2009. Thirty nine samples in this study were taken by several criteria. Statistical analysis tool used in this research was logistic regression with a significance level of 5%. From the test result, it was obtained that either partially or simultaneously, company size, intensity of inventory, price variability of goods sold, and income variability have a significance level above 5%. This shows that these variables did not significantly influence the selection method of inventory valuation.

  9. Fuzzy multiple linear regression: A computational approach

    Science.gov (United States)

    Juang, C. H.; Huang, X. H.; Fleming, J. W.

    1992-01-01

    This paper presents a new computational approach for performing fuzzy regression. In contrast to Bardossy's approach, the new approach, while dealing with fuzzy variables, closely follows the conventional regression technique. In this approach, treatment of fuzzy input is more 'computational' than 'symbolic.' The following sections first outline the formulation of the new approach, then deal with the implementation and computational scheme, and this is followed by examples to illustrate the new procedure.

  10. Multi-step polynomial regression method to model and forecast malaria incidence.

    Directory of Open Access Journals (Sweden)

    Chandrajit Chatterjee

    Full Text Available Malaria is one of the most severe problems faced by the world even today. Understanding the causative factors such as age, sex, social factors, environmental variability etc. as well as underlying transmission dynamics of the disease is important for epidemiological research on malaria and its eradication. Thus, development of suitable modeling approach and methodology, based on the available data on the incidence of the disease and other related factors is of utmost importance. In this study, we developed a simple non-linear regression methodology in modeling and forecasting malaria incidence in Chennai city, India, and predicted future disease incidence with high confidence level. We considered three types of data to develop the regression methodology: a longer time series data of Slide Positivity Rates (SPR of malaria; a smaller time series data (deaths due to Plasmodium vivax of one year; and spatial data (zonal distribution of P. vivax deaths for the city along with the climatic factors, population and previous incidence of the disease. We performed variable selection by simple correlation study, identification of the initial relationship between variables through non-linear curve fitting and used multi-step methods for induction of variables in the non-linear regression analysis along with applied Gauss-Markov models, and ANOVA for testing the prediction, validity and constructing the confidence intervals. The results execute the applicability of our method for different types of data, the autoregressive nature of forecasting, and show high prediction power for both SPR and P. vivax deaths, where the one-lag SPR values plays an influential role and proves useful for better prediction. Different climatic factors are identified as playing crucial role on shaping the disease curve. Further, disease incidence at zonal level and the effect of causative factors on different zonal clusters indicate the pattern of malaria prevalence in the city

  11. Variable selection for confounder control, flexible modeling and Collaborative Targeted Minimum Loss-based Estimation in causal inference

    Science.gov (United States)

    Schnitzer, Mireille E.; Lok, Judith J.; Gruber, Susan

    2015-01-01

    This paper investigates the appropriateness of the integration of flexible propensity score modeling (nonparametric or machine learning approaches) in semiparametric models for the estimation of a causal quantity, such as the mean outcome under treatment. We begin with an overview of some of the issues involved in knowledge-based and statistical variable selection in causal inference and the potential pitfalls of automated selection based on the fit of the propensity score. Using a simple example, we directly show the consequences of adjusting for pure causes of the exposure when using inverse probability of treatment weighting (IPTW). Such variables are likely to be selected when using a naive approach to model selection for the propensity score. We describe how the method of Collaborative Targeted minimum loss-based estimation (C-TMLE; van der Laan and Gruber, 2010) capitalizes on the collaborative double robustness property of semiparametric efficient estimators to select covariates for the propensity score based on the error in the conditional outcome model. Finally, we compare several approaches to automated variable selection in low-and high-dimensional settings through a simulation study. From this simulation study, we conclude that using IPTW with flexible prediction for the propensity score can result in inferior estimation, while Targeted minimum loss-based estimation and C-TMLE may benefit from flexible prediction and remain robust to the presence of variables that are highly correlated with treatment. However, in our study, standard influence function-based methods for the variance underestimated the standard errors, resulting in poor coverage under certain data-generating scenarios. PMID:26226129

  12. Testing homogeneity in Weibull-regression models.

    Science.gov (United States)

    Bolfarine, Heleno; Valença, Dione M

    2005-10-01

    In survival studies with families or geographical units it may be of interest testing whether such groups are homogeneous for given explanatory variables. In this paper we consider score type tests for group homogeneity based on a mixing model in which the group effect is modelled as a random variable. As opposed to hazard-based frailty models, this model presents survival times that conditioned on the random effect, has an accelerated failure time representation. The test statistics requires only estimation of the conventional regression model without the random effect and does not require specifying the distribution of the random effect. The tests are derived for a Weibull regression model and in the uncensored situation, a closed form is obtained for the test statistic. A simulation study is used for comparing the power of the tests. The proposed tests are applied to real data sets with censored data.

  13. Selection of variables for neural network analysis. Comparisons of several methods with high energy physics data

    International Nuclear Information System (INIS)

    Proriol, J.

    1994-01-01

    Five different methods are compared for selecting the most important variables with a view to classifying high energy physics events with neural networks. The different methods are: the F-test, Principal Component Analysis (PCA), a decision tree method: CART, weight evaluation, and Optimal Cell Damage (OCD). The neural networks use the variables selected with the different methods. We compare the percentages of events properly classified by each neural network. The learning set and the test set are the same for all the neural networks. (author)

  14. An Analysis of the Effectiveness of Supplemental Instruction: The Problem of Selection Bias and Limited Dependent Variables

    Science.gov (United States)

    Bowles, Tyler J.; Jones, Jason

    2004-01-01

    Single equation regression models have been used rather extensively to test the effectiveness of Supplemental Instruction (SI). This approach, however, fails to account for the possibility that SI attendance and the outcome of SI attendance are jointly determined endogenous variables. Moreover, the standard approach fails to account for the fact…

  15. Demographic Variables and Selective, Sustained Attention and Planning through Cognitive Tasks among Healthy Adults

    Directory of Open Access Journals (Sweden)

    Afsaneh Zarghi

    2011-04-01

    Full Text Available Introduction: Cognitive tasks are considered to be applicable and appropriate in assessing cognitive domains. The purpose of our study is to determine the relationship existence between variables of age, sex and education with selective, sustained attention and planning abilities by means of computerized cognitive tasks among healthy adults. Methods: A cross-sectional study was implemented during 6 months from June to November, 2010 on 84 healthy adults (42 male and 42 female. The whole participants performed computerized CPT, STROOP and TOL tests after being content and trained. Results: The obtained data indicate that there is a significant correlation coefficient between age, sex and education variables (p<0.05. Discussion: The above-mentioned tests can be used to assess selective, sustained attention and planning.

  16. Common pitfalls in statistical analysis: Linear regression analysis

    Directory of Open Access Journals (Sweden)

    Rakesh Aggarwal

    2017-01-01

    Full Text Available In a previous article in this series, we explained correlation analysis which describes the strength of relationship between two continuous variables. In this article, we deal with linear regression analysis which predicts the value of one continuous variable from another. We also discuss the assumptions and pitfalls associated with this analysis.

  17. Logistic regression modelling: procedures and pitfalls in developing and interpreting prediction models

    Directory of Open Access Journals (Sweden)

    Nataša Šarlija

    2017-01-01

    Full Text Available This study sheds light on the most common issues related to applying logistic regression in prediction models for company growth. The purpose of the paper is 1 to provide a detailed demonstration of the steps in developing a growth prediction model based on logistic regression analysis, 2 to discuss common pitfalls and methodological errors in developing a model, and 3 to provide solutions and possible ways of overcoming these issues. Special attention is devoted to the question of satisfying logistic regression assumptions, selecting and defining dependent and independent variables, using classification tables and ROC curves, for reporting model strength, interpreting odds ratios as effect measures and evaluating performance of the prediction model. Development of a logistic regression model in this paper focuses on a prediction model of company growth. The analysis is based on predominantly financial data from a sample of 1471 small and medium-sized Croatian companies active between 2009 and 2014. The financial data is presented in the form of financial ratios divided into nine main groups depicting following areas of business: liquidity, leverage, activity, profitability, research and development, investing and export. The growth prediction model indicates aspects of a business critical for achieving high growth. In that respect, the contribution of this paper is twofold. First, methodological, in terms of pointing out pitfalls and potential solutions in logistic regression modelling, and secondly, theoretical, in terms of identifying factors responsible for high growth of small and medium-sized companies.

  18. Effects of musical tempo on physiological, affective, and perceptual variables and performance of self-selected walking pace.

    Science.gov (United States)

    Almeida, Flávia Angélica Martins; Nunes, Renan Felipe Hartmann; Ferreira, Sandro Dos Santos; Krinski, Kleverton; Elsangedy, Hassan Mohamed; Buzzachera, Cosme Franklin; Alves, Ragami Chaves; Gregorio da Silva, Sergio

    2015-06-01

    [Purpose] This study investigated the effects of musical tempo on physiological, affective, and perceptual responses as well as the performance of self-selected walking pace. [Subjects] The study included 28 adult women between 29 and 51 years old. [Methods] The subjects were divided into three groups: no musical stimulation group (control), and 90 and 140 beats per minute musical tempo groups. Each subject underwent three experimental sessions: involved familiarization with the equipment, an incremental test to exhaustion, and a 30-min walk on a treadmill at a self-selected pace, respectively. During the self-selected walking session, physiological, perceptual, and affective variables were evaluated, and walking performance was evaluated at the end. [Results] There were no significant differences in physiological variables or affective response among groups. However, there were significant differences in perceptual response and walking performance among groups. [Conclusion] Fast music (140 beats per minute) promotes a higher rating of perceived exertion and greater performance in self-selected walking pace without significantly altering physiological variables or affective response.

  19. Sparse modeling of spatial environmental variables associated with asthma.

    Science.gov (United States)

    Chang, Timothy S; Gangnon, Ronald E; David Page, C; Buckingham, William R; Tandias, Aman; Cowan, Kelly J; Tomasallo, Carrie D; Arndt, Brian G; Hanrahan, Lawrence P; Guilbert, Theresa W

    2015-02-01

    Geographically distributed environmental factors influence the burden of diseases such as asthma. Our objective was to identify sparse environmental variables associated with asthma diagnosis gathered from a large electronic health record (EHR) dataset while controlling for spatial variation. An EHR dataset from the University of Wisconsin's Family Medicine, Internal Medicine and Pediatrics Departments was obtained for 199,220 patients aged 5-50years over a three-year period. Each patient's home address was geocoded to one of 3456 geographic census block groups. Over one thousand block group variables were obtained from a commercial database. We developed a Sparse Spatial Environmental Analysis (SASEA). Using this method, the environmental variables were first dimensionally reduced with sparse principal component analysis. Logistic thin plate regression spline modeling was then used to identify block group variables associated with asthma from sparse principal components. The addresses of patients from the EHR dataset were distributed throughout the majority of Wisconsin's geography. Logistic thin plate regression spline modeling captured spatial variation of asthma. Four sparse principal components identified via model selection consisted of food at home, dog ownership, household size, and disposable income variables. In rural areas, dog ownership and renter occupied housing units from significant sparse principal components were associated with asthma. Our main contribution is the incorporation of sparsity in spatial modeling. SASEA sequentially added sparse principal components to Logistic thin plate regression spline modeling. This method allowed association of geographically distributed environmental factors with asthma using EHR and environmental datasets. SASEA can be applied to other diseases with environmental risk factors. Copyright © 2014 Elsevier Inc. All rights reserved.

  20. New strategy for determination of anthocyanins, polyphenols and antioxidant capacity of Brassica oleracea liquid extract using infrared spectroscopies and multivariate regression

    Science.gov (United States)

    de Oliveira, Isadora R. N.; Roque, Jussara V.; Maia, Mariza P.; Stringheta, Paulo C.; Teófilo, Reinaldo F.

    2018-04-01

    A new method was developed to determine the antioxidant properties of red cabbage extract (Brassica oleracea) by mid (MID) and near (NIR) infrared spectroscopies and partial least squares (PLS) regression. A 70% (v/v) ethanolic extract of red cabbage was concentrated to 9° Brix and further diluted (12 to 100%) in water. The dilutions were used as external standards for the building of PLS models. For the first time, this strategy was applied for building multivariate regression models. Reference analyses and spectral data were obtained from diluted extracts. The determinate properties were total and monomeric anthocyanins, total polyphenols and antioxidant capacity by ABTS (2,2-azino-bis(3-ethyl-benzothiazoline-6-sulfonate)) and DPPH (2,2-diphenyl-1-picrylhydrazyl) methods. Ordered predictors selection (OPS) and genetic algorithm (GA) were used for feature selection before PLS regression (PLS-1). In addition, a PLS-2 regression was applied to all properties simultaneously. PLS-1 models provided more predictive models than did PLS-2 regression. PLS-OPS and PLS-GA models presented excellent prediction results with a correlation coefficient higher than 0.98. However, the best models were obtained using PLS and variable selection with the OPS algorithm and the models based on NIR spectra were considered more predictive for all properties. Then, these models provided a simple, rapid and accurate method for determination of red cabbage extract antioxidant properties and its suitability for use in the food industry.

  1. Spatial variability in levels of benzene, formaldehyde, and total benzene, toluene, ethylbenzene and xylenes in New York City: a land-use regression study.

    Science.gov (United States)

    Kheirbek, Iyad; Johnson, Sarah; Ross, Zev; Pezeshki, Grant; Ito, Kazuhiko; Eisl, Holger; Matte, Thomas

    2012-07-31

    Hazardous air pollutant exposures are common in urban areas contributing to increased risk of cancer and other adverse health outcomes. While recent analyses indicate that New York City residents experience significantly higher cancer risks attributable to hazardous air pollutant exposures than the United States as a whole, limited data exist to assess intra-urban variability in air toxics exposures. To assess intra-urban spatial variability in exposures to common hazardous air pollutants, street-level air sampling for volatile organic compounds and aldehydes was conducted at 70 sites throughout New York City during the spring of 2011. Land-use regression models were developed using a subset of 59 sites and validated against the remaining 11 sites to describe the relationship between concentrations of benzene, total BTEX (benzene, toluene, ethylbenzene, xylenes) and formaldehyde to indicators of local sources, adjusting for temporal variation. Total BTEX levels exhibited the most spatial variability, followed by benzene and formaldehyde (coefficient of variation of temporally adjusted measurements of 0.57, 0.35, 0.22, respectively). Total roadway length within 100 m, traffic signal density within 400 m of monitoring sites, and an indicator of temporal variation explained 65% of the total variability in benzene while 70% of the total variability in BTEX was accounted for by traffic signal density within 450 m, density of permitted solvent-use industries within 500 m, and an indicator of temporal variation. Measures of temporal variation, traffic signal density within 400 m, road length within 100 m, and interior building area within 100 m (indicator of heating fuel combustion) predicted 83% of the total variability of formaldehyde. The models built with the modeling subset were found to predict concentrations well, predicting 62% to 68% of monitored values at validation sites. Traffic and point source emissions cause substantial variation in street-level exposures

  2. Association between biomarkers and clinical characteristics in chronic subdural hematoma patients assessed with lasso regression.

    Directory of Open Access Journals (Sweden)

    Are Hugo Pripp

    Full Text Available Chronic subdural hematoma (CSDH is characterized by an "old" encapsulated collection of blood and blood breakdown products between the brain and its outermost covering (the dura. Recognized risk factors for development of CSDH are head injury, old age and using anticoagulation medication, but its underlying pathophysiological processes are still unclear. It is assumed that a complex local process of interrelated mechanisms including inflammation, neomembrane formation, angiogenesis and fibrinolysis could be related to its development and propagation. However, the association between the biomarkers of inflammation and angiogenesis, and the clinical and radiological characteristics of CSDH patients, need further investigation. The high number of biomarkers compared to the number of observations, the correlation between biomarkers, missing data and skewed distributions may limit the usefulness of classical statistical methods. We therefore explored lasso regression to assess the association between 30 biomarkers of inflammation and angiogenesis at the site of lesions, and selected clinical and radiological characteristics in a cohort of 93 patients. Lasso regression performs both variable selection and regularization to improve the predictive accuracy and interpretability of the statistical model. The results from the lasso regression showed analysis exhibited lack of robust statistical association between the biomarkers in hematoma fluid with age, gender, brain infarct, neurological deficiencies and volume of hematoma. However, there were associations between several of the biomarkers with postoperative recurrence requiring reoperation. The statistical analysis with lasso regression supported previous findings that the immunological characteristics of CSDH are local. The relationship between biomarkers, the radiological appearance of lesions and recurrence requiring reoperation have been inclusive using classical statistical methods on these data

  3. A hybrid approach of stepwise regression, logistic regression, support vector machine, and decision tree for forecasting fraudulent financial statements.

    Science.gov (United States)

    Chen, Suduan; Goo, Yeong-Jia James; Shen, Zone-De

    2014-01-01

    As the fraudulent financial statement of an enterprise is increasingly serious with each passing day, establishing a valid forecasting fraudulent financial statement model of an enterprise has become an important question for academic research and financial practice. After screening the important variables using the stepwise regression, the study also matches the logistic regression, support vector machine, and decision tree to construct the classification models to make a comparison. The study adopts financial and nonfinancial variables to assist in establishment of the forecasting fraudulent financial statement model. Research objects are the companies to which the fraudulent and nonfraudulent financial statement happened between years 1998 to 2012. The findings are that financial and nonfinancial information are effectively used to distinguish the fraudulent financial statement, and decision tree C5.0 has the best classification effect 85.71%.

  4. Development of nondestructive detection method for adulterated powder products using Raman spectroscopy and partial least squares regression

    Energy Technology Data Exchange (ETDEWEB)

    Lee, Sang Dae; Lohumi, Santosh; Cho, Byoung Kwan [Dept. of Biosystems Machinery Engineering, Chungnam National University, Daejeon (Korea, Republic of); Kim, Moon Sung [United States Department of Agriculture Agricultural Research Service, Washington (United States); Lee, Soo Hee [Life and Technology Co.,Ltd., Hwasung (Korea, Republic of)

    2014-08-15

    This study was conducted to develop a non-destructive detection method for adulterated powder products using Raman spectroscopy and partial least squares regression(PLSR). Garlic and ginger powder, which are used as natural seasoning and in health supplement foods, were selected for this experiment. Samples were adulterated with corn starch in concentrations of 5-35%. PLSR models for adulterated garlic and ginger powders were developed and their performances evaluated using cross validation. The R{sup 2}{sub c} and SEC of an optimal PLSR model were 0.99 and 2.16 for the garlic powder samples, and 0.99 and 0.84 for the ginger samples, respectively. The variable importance in projection (VIP) score is a useful and simple tool for the evaluation of the importance of each variable in a PLSR model. After the VIP scores were taken pre-selection, the Raman spectrum data was reduced by one third. New PLSR models, based on a reduced number of wavelengths selected by the VIP scores technique, gave good predictions for the adulterated garlic and ginger powder samples.

  5. Development of nondestructive detection method for adulterated powder products using Raman spectroscopy and partial least squares regression

    International Nuclear Information System (INIS)

    Lee, Sang Dae; Lohumi, Santosh; Cho, Byoung Kwan; Kim, Moon Sung; Lee, Soo Hee

    2014-01-01

    This study was conducted to develop a non-destructive detection method for adulterated powder products using Raman spectroscopy and partial least squares regression(PLSR). Garlic and ginger powder, which are used as natural seasoning and in health supplement foods, were selected for this experiment. Samples were adulterated with corn starch in concentrations of 5-35%. PLSR models for adulterated garlic and ginger powders were developed and their performances evaluated using cross validation. The R 2 c and SEC of an optimal PLSR model were 0.99 and 2.16 for the garlic powder samples, and 0.99 and 0.84 for the ginger samples, respectively. The variable importance in projection (VIP) score is a useful and simple tool for the evaluation of the importance of each variable in a PLSR model. After the VIP scores were taken pre-selection, the Raman spectrum data was reduced by one third. New PLSR models, based on a reduced number of wavelengths selected by the VIP scores technique, gave good predictions for the adulterated garlic and ginger powder samples.

  6. The Determinants of Equity Risk and Their Forecasting Implications: A Quantile Regression Perspective

    Directory of Open Access Journals (Sweden)

    Giovanni Bonaccolto

    2016-07-01

    Full Text Available Several market and macro-level variables influence the evolution of equity risk in addition to the well-known volatility persistence. However, the impact of those covariates might change depending on the risk level, being different between low and high volatility states. By combining equity risk estimates, obtained from the Realized Range Volatility, corrected for microstructure noise and jumps, and quantile regression methods, we evaluate the forecasting implications of the equity risk determinants in different volatility states and, without distributional assumptions on the realized range innovations, we recover both the points and the conditional distribution forecasts. In addition, we analyse how the the relationships among the involved variables evolve over time, through a rolling window procedure. The results show evidence of the selected variables’ relevant impacts and, particularly during periods of market stress, highlight heterogeneous effects across quantiles.

  7. Kepler AutoRegressive Planet Search (KARPS)

    Science.gov (United States)

    Caceres, Gabriel

    2018-01-01

    One of the main obstacles in detecting faint planetary transits is the intrinsic stellar variability of the host star. The Kepler AutoRegressive Planet Search (KARPS) project implements statistical methodology associated with autoregressive processes (in particular, ARIMA and ARFIMA) to model stellar lightcurves in order to improve exoplanet transit detection. We also develop a novel Transit Comb Filter (TCF) applied to the AR residuals which provides a periodogram analogous to the standard Box-fitting Least Squares (BLS) periodogram. We train a random forest classifier on known Kepler Objects of Interest (KOIs) using select features from different stages of this analysis, and then use ROC curves to define and calibrate the criteria to recover the KOI planet candidates with high fidelity. These statistical methods are detailed in a contributed poster (Feigelson et al., this meeting).These procedures are applied to the full DR25 dataset of NASA’s Kepler mission. Using the classification criteria, a vast majority of known KOIs are recovered and dozens of new KARPS Candidate Planets (KCPs) discovered, including ultra-short period exoplanets. The KCPs will be briefly presented and discussed.

  8. Group-wise partial least square regression

    NARCIS (Netherlands)

    Camacho, José; Saccenti, Edoardo

    2018-01-01

    This paper introduces the group-wise partial least squares (GPLS) regression. GPLS is a new sparse PLS technique where the sparsity structure is defined in terms of groups of correlated variables, similarly to what is done in the related group-wise principal component analysis. These groups are

  9. Selective attention deficits in obsessive-compulsive disorder: the role of metacognitive processes.

    Science.gov (United States)

    Koch, Julia; Exner, Cornelia

    2015-02-28

    While initial studies supported the hypothesis that cognitive characteristics that capture cognitive resources act as underlying mechanisms in memory deficits in obsessive-compulsive disorder (OCD), the influence of those characteristics on selective attention has not been studied, yet. In this study, we examined the influence of cognitive self-consciousness (CSC), rumination and worrying on performance in selective attention in OCD and compared the results to a depressive and a healthy control group. We found that 36 OCD and 36 depressive participants were impaired in selective attention in comparison to 36 healthy controls. In all groups, hierarchical regression analyses demonstrated that age, intelligence and years in school significantly predicted performance in selective attention. But only in OCD, the predictive power of the regression model was improved when CSC, rumination and worrying were implemented as predictor variables. In contrast, in none of the three groups the predictive power improved when indicators of severity of obsessive-compulsive (OC) and depressive symptoms and trait anxiety were introduced as predictor variables. Thus, our results support the assumption that mental characteristics that bind cognitive resources play an important role in the understanding of selective attention deficits in OCD and that this mechanism is especially relevant for OCD. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

  10. Variable Selection in Heterogeneous Datasets: A Truncated-rank Sparse Linear Mixed Model with Applications to Genome-wide Association Studies.

    Science.gov (United States)

    Wang, Haohan; Aragam, Bryon; Xing, Eric P

    2018-04-26

    A fundamental and important challenge in modern datasets of ever increasing dimensionality is variable selection, which has taken on renewed interest recently due to the growth of biological and medical datasets with complex, non-i.i.d. structures. Naïvely applying classical variable selection methods such as the Lasso to such datasets may lead to a large number of false discoveries. Motivated by genome-wide association studies in genetics, we study the problem of variable selection for datasets arising from multiple subpopulations, when this underlying population structure is unknown to the researcher. We propose a unified framework for sparse variable selection that adaptively corrects for population structure via a low-rank linear mixed model. Most importantly, the proposed method does not require prior knowledge of sample structure in the data and adaptively selects a covariance structure of the correct complexity. Through extensive experiments, we illustrate the effectiveness of this framework over existing methods. Further, we test our method on three different genomic datasets from plants, mice, and human, and discuss the knowledge we discover with our method. Copyright © 2018. Published by Elsevier Inc.

  11. Non-stationary hydrologic frequency analysis using B-spline quantile regression

    Science.gov (United States)

    Nasri, B.; Bouezmarni, T.; St-Hilaire, A.; Ouarda, T. B. M. J.

    2017-11-01

    Hydrologic frequency analysis is commonly used by engineers and hydrologists to provide the basic information on planning, design and management of hydraulic and water resources systems under the assumption of stationarity. However, with increasing evidence of climate change, it is possible that the assumption of stationarity, which is prerequisite for traditional frequency analysis and hence, the results of conventional analysis would become questionable. In this study, we consider a framework for frequency analysis of extremes based on B-Spline quantile regression which allows to model data in the presence of non-stationarity and/or dependence on covariates with linear and non-linear dependence. A Markov Chain Monte Carlo (MCMC) algorithm was used to estimate quantiles and their posterior distributions. A coefficient of determination and Bayesian information criterion (BIC) for quantile regression are used in order to select the best model, i.e. for each quantile, we choose the degree and number of knots of the adequate B-spline quantile regression model. The method is applied to annual maximum and minimum streamflow records in Ontario, Canada. Climate indices are considered to describe the non-stationarity in the variable of interest and to estimate the quantiles in this case. The results show large differences between the non-stationary quantiles and their stationary equivalents for an annual maximum and minimum discharge with high annual non-exceedance probabilities.

  12. About hidden influence of predictor variables: Suppressor and mediator variables

    Directory of Open Access Journals (Sweden)

    Milovanović Boško

    2013-01-01

    Full Text Available In this paper procedure for researching hidden influence of predictor variables in regression models and depicting suppressor variables and mediator variables is shown. It is also shown that detection of suppressor variables and mediator variables could provide refined information about the research problem. As an example for applying this procedure, relation between Atlantic atmospheric centers and air temperature and precipitation amount in Serbia is chosen. [Projekat Ministarstva nauke Republike Srbije, br. 47007

  13. Application of the step-wise regression procedure to the semi-empirical formulae of the nuclear binding energy

    International Nuclear Information System (INIS)

    Eissa, E.A.; Ayad, M.; Gashier, F.A.B.

    1984-01-01

    Most of the binding energy semi-empirical terms without the deformation corrections used by P.A. Seeger are arranged in a multiple linear regression form. The stepwise regression procedure with 95% confidence levels for acceptance and rejection of variables is applied for seeking a model for calculating binding energies of even-even (E-E) nuclei through a significance testing of each basic term. Partial F-values are taken as estimates for the significance of each term. The residual standard deviation and the overall F-value are used for selecting the best linear regression model. (E-E) nuclei are taken into sets lying between two successive proton and neutron magic numbers. The present work is in favour of the magic number 126 followed by 164 for the neutrons and indecisive in supporting the recently predicted proton magic number 114 rather than the previous one, 126. (author)

  14. The Predictive Value of Selection Criteria in an Urban Magnet School

    Science.gov (United States)

    Lohmeier, Jill Hendrickson; Raad, Jennifer

    2012-01-01

    The predictive value of selection criteria on outcome data from two cohorts of students (Total N = 525) accepted to an urban magnet high school were evaluated. Regression analyses of typical screening variables (suspensions, absences, metropolitan achievement tests, middle school grade point averages [GPAs], Matrix Analogies test scores, and…

  15. The intermediate endpoint effect in logistic and probit regression

    Science.gov (United States)

    MacKinnon, DP; Lockwood, CM; Brown, CH; Wang, W; Hoffman, JM

    2010-01-01

    Background An intermediate endpoint is hypothesized to be in the middle of the causal sequence relating an independent variable to a dependent variable. The intermediate variable is also called a surrogate or mediating variable and the corresponding effect is called the mediated, surrogate endpoint, or intermediate endpoint effect. Clinical studies are often designed to change an intermediate or surrogate endpoint and through this intermediate change influence the ultimate endpoint. In many intermediate endpoint clinical studies the dependent variable is binary, and logistic or probit regression is used. Purpose The purpose of this study is to describe a limitation of a widely used approach to assessing intermediate endpoint effects and to propose an alternative method, based on products of coefficients, that yields more accurate results. Methods The intermediate endpoint model for a binary outcome is described for a true binary outcome and for a dichotomization of a latent continuous outcome. Plots of true values and a simulation study are used to evaluate the different methods. Results Distorted estimates of the intermediate endpoint effect and incorrect conclusions can result from the application of widely used methods to assess the intermediate endpoint effect. The same problem occurs for the proportion of an effect explained by an intermediate endpoint, which has been suggested as a useful measure for identifying intermediate endpoints. A solution to this problem is given based on the relationship between latent variable modeling and logistic or probit regression. Limitations More complicated intermediate variable models are not addressed in the study, although the methods described in the article can be extended to these more complicated models. Conclusions Researchers are encouraged to use an intermediate endpoint method based on the product of regression coefficients. A common method based on difference in coefficient methods can lead to distorted

  16. Multicollinearity is a red herring in the search for moderator variables: A guide to interpreting moderated multiple regression models and a critique of Iacobucci, Schneider, Popovich, and Bakamitsos (2016).

    Science.gov (United States)

    McClelland, Gary H; Irwin, Julie R; Disatnik, David; Sivan, Liron

    2017-02-01

    Multicollinearity is irrelevant to the search for moderator variables, contrary to the implications of Iacobucci, Schneider, Popovich, and Bakamitsos (Behavior Research Methods, 2016, this issue). Multicollinearity is like the red herring in a mystery novel that distracts the statistical detective from the pursuit of a true moderator relationship. We show multicollinearity is completely irrelevant for tests of moderator variables. Furthermore, readers of Iacobucci et al. might be confused by a number of their errors. We note those errors, but more positively, we describe a variety of methods researchers might use to test and interpret their moderated multiple regression models, including two-stage testing, mean-centering, spotlighting, orthogonalizing, and floodlighting without regard to putative issues of multicollinearity. We cite a number of recent studies in the psychological literature in which the researchers used these methods appropriately to test, to interpret, and to report their moderated multiple regression models. We conclude with a set of recommendations for the analysis and reporting of moderated multiple regression that should help researchers better understand their models and facilitate generalizations across studies.

  17. Descriptor Learning via Supervised Manifold Regularization for Multioutput Regression.

    Science.gov (United States)

    Zhen, Xiantong; Yu, Mengyang; Islam, Ali; Bhaduri, Mousumi; Chan, Ian; Li, Shuo

    2017-09-01

    Multioutput regression has recently shown great ability to solve challenging problems in both computer vision and medical image analysis. However, due to the huge image variability and ambiguity, it is fundamentally challenging to handle the highly complex input-target relationship of multioutput regression, especially with indiscriminate high-dimensional representations. In this paper, we propose a novel supervised descriptor learning (SDL) algorithm for multioutput regression, which can establish discriminative and compact feature representations to improve the multivariate estimation performance. The SDL is formulated as generalized low-rank approximations of matrices with a supervised manifold regularization. The SDL is able to simultaneously extract discriminative features closely related to multivariate targets and remove irrelevant and redundant information by transforming raw features into a new low-dimensional space aligned to targets. The achieved discriminative while compact descriptor largely reduces the variability and ambiguity for multioutput regression, which enables more accurate and efficient multivariate estimation. We conduct extensive evaluation of the proposed SDL on both synthetic data and real-world multioutput regression tasks for both computer vision and medical image analysis. Experimental results have shown that the proposed SDL can achieve high multivariate estimation accuracy on all tasks and largely outperforms the algorithms in the state of the arts. Our method establishes a novel SDL framework for multioutput regression, which can be widely used to boost the performance in different applications.

  18. Model selection for marginal regression analysis of longitudinal data with missing observations and covariate measurement error.

    Science.gov (United States)

    Shen, Chung-Wei; Chen, Yi-Hau

    2015-10-01

    Missing observations and covariate measurement error commonly arise in longitudinal data. However, existing methods for model selection in marginal regression analysis of longitudinal data fail to address the potential bias resulting from these issues. To tackle this problem, we propose a new model selection criterion, the Generalized Longitudinal Information Criterion, which is based on an approximately unbiased estimator for the expected quadratic error of a considered marginal model accounting for both data missingness and covariate measurement error. The simulation results reveal that the proposed method performs quite well in the presence of missing data and covariate measurement error. On the contrary, the naive procedures without taking care of such complexity in data may perform quite poorly. The proposed method is applied to data from the Taiwan Longitudinal Study on Aging to assess the relationship of depression with health and social status in the elderly, accommodating measurement error in the covariate as well as missing observations. © The Author 2015. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

  19. Chaotic Dynamical State Variables Selection Procedure Based Image Encryption Scheme

    Directory of Open Access Journals (Sweden)

    Zia Bashir

    2017-12-01

    Full Text Available Nowadays, in the modern digital era, the use of computer technologies such as smartphones, tablets and the Internet, as well as the enormous quantity of confidential information being converted into digital form have resulted in raised security issues. This, in turn, has led to rapid developments in cryptography, due to the imminent need for system security. Low-dimensional chaotic systems have low complexity and key space, yet they achieve high encryption speed. An image encryption scheme is proposed that, without compromising the security, uses reasonable resources. We introduced a chaotic dynamic state variables selection procedure (CDSVSP to use all state variables of a hyper-chaotic four-dimensional dynamical system. As a result, less iterations of the dynamical system are required, and resources are saved, thus making the algorithm fast and suitable for practical use. The simulation results of security and other miscellaneous tests demonstrate that the suggested algorithm excels at robustness, security and high speed encryption.

  20. Poisson Regression Analysis of Illness and Injury Surveillance Data

    Energy Technology Data Exchange (ETDEWEB)

    Frome E.L., Watkins J.P., Ellis E.D.

    2012-12-12

    The Department of Energy (DOE) uses illness and injury surveillance to monitor morbidity and assess the overall health of the work force. Data collected from each participating site include health events and a roster file with demographic information. The source data files are maintained in a relational data base, and are used to obtain stratified tables of health event counts and person time at risk that serve as the starting point for Poisson regression analysis. The explanatory variables that define these tables are age, gender, occupational group, and time. Typical response variables of interest are the number of absences due to illness or injury, i.e., the response variable is a count. Poisson regression methods are used to describe the effect of the explanatory variables on the health event rates using a log-linear main effects model. Results of fitting the main effects model are summarized in a tabular and graphical form and interpretation of model parameters is provided. An analysis of deviance table is used to evaluate the importance of each of the explanatory variables on the event rate of interest and to determine if interaction terms should be considered in the analysis. Although Poisson regression methods are widely used in the analysis of count data, there are situations in which over-dispersion occurs. This could be due to lack-of-fit of the regression model, extra-Poisson variation, or both. A score test statistic and regression diagnostics are used to identify over-dispersion. A quasi-likelihood method of moments procedure is used to evaluate and adjust for extra-Poisson variation when necessary. Two examples are presented using respiratory disease absence rates at two DOE sites to illustrate the methods and interpretation of the results. In the first example the Poisson main effects model is adequate. In the second example the score test indicates considerable over-dispersion and a more detailed analysis attributes the over-dispersion to extra

  1. Cataclysmic variables from a ROSAT/2MASS selection - I. Four new intermediate polars

    NARCIS (Netherlands)

    Gänsicke, B.T.; Marsh, T.R.; Edge, A.; Rodríguez-Gil, P.; Steeghs, D.; Araujo-Betancor, S.; Harlaftis, E.; Giannakis, O.; Pyrzas, S.; Morales-Rueda, L.; Aungwerojwit, A.

    2005-01-01

    We report the first results from a new search for cataclysmic variables (CVs) using a combined X-ray (ROSAT)/infrared (2MASS) target selection that discriminates against background active galactic nuclei. Identification spectra were obtained at the Isaac Newton Telescope for a total of 174 targets,

  2. Incorporating wind availability into land use regression modelling of air quality in mountainous high-density urban environment.

    Science.gov (United States)

    Shi, Yuan; Lau, Kevin Ka-Lun; Ng, Edward

    2017-08-01

    Urban air quality serves as an important function of the quality of urban life. Land use regression (LUR) modelling of air quality is essential for conducting health impacts assessment but more challenging in mountainous high-density urban scenario due to the complexities of the urban environment. In this study, a total of 21 LUR models are developed for seven kinds of air pollutants (gaseous air pollutants CO, NO 2 , NO x , O 3 , SO 2 and particulate air pollutants PM 2.5 , PM 10 ) with reference to three different time periods (summertime, wintertime and annual average of 5-year long-term hourly monitoring data from local air quality monitoring network) in Hong Kong. Under the mountainous high-density urban scenario, we improved the traditional LUR modelling method by incorporating wind availability information into LUR modelling based on surface geomorphometrical analysis. As a result, 269 independent variables were examined to develop the LUR models by using the "ADDRESS" independent variable selection method and stepwise multiple linear regression (MLR). Cross validation has been performed for each resultant model. The results show that wind-related variables are included in most of the resultant models as statistically significant independent variables. Compared with the traditional method, a maximum increase of 20% was achieved in the prediction performance of annual averaged NO 2 concentration level by incorporating wind-related variables into LUR model development. Copyright © 2017 Elsevier Inc. All rights reserved.

  3. SPSS macros to compare any two fitted values from a regression model.

    Science.gov (United States)

    Weaver, Bruce; Dubois, Sacha

    2012-12-01

    In regression models with first-order terms only, the coefficient for a given variable is typically interpreted as the change in the fitted value of Y for a one-unit increase in that variable, with all other variables held constant. Therefore, each regression coefficient represents the difference between two fitted values of Y. But the coefficients represent only a fraction of the possible fitted value comparisons that might be of interest to researchers. For many fitted value comparisons that are not captured by any of the regression coefficients, common statistical software packages do not provide the standard errors needed to compute confidence intervals or carry out statistical tests-particularly in more complex models that include interactions, polynomial terms, or regression splines. We describe two SPSS macros that implement a matrix algebra method for comparing any two fitted values from a regression model. The !OLScomp and !MLEcomp macros are for use with models fitted via ordinary least squares and maximum likelihood estimation, respectively. The output from the macros includes the standard error of the difference between the two fitted values, a 95% confidence interval for the difference, and a corresponding statistical test with its p-value.

  4. Regression Methods for Virtual Metrology of Layer Thickness in Chemical Vapor Deposition

    DEFF Research Database (Denmark)

    Purwins, Hendrik; Barak, Bernd; Nagi, Ahmed

    2014-01-01

    The quality of wafer production in semiconductor manufacturing cannot always be monitored by a costly physical measurement. Instead of measuring a quantity directly, it can be predicted by a regression method (Virtual Metrology). In this paper, a survey on regression methods is given to predict...... average Silicon Nitride cap layer thickness for the Plasma Enhanced Chemical Vapor Deposition (PECVD) dual-layer metal passivation stack process. Process and production equipment Fault Detection and Classification (FDC) data are used as predictor variables. Various variable sets are compared: one most...... algorithm, and Support Vector Regression (SVR). On a test set, SVR outperforms the other methods by a large margin, being more robust towards changes in the production conditions. The method performs better on high-dimensional multivariate input data than on the most predictive variables alone. Process...

  5. Multiple Response Regression for Gaussian Mixture Models with Known Labels.

    Science.gov (United States)

    Lee, Wonyul; Du, Ying; Sun, Wei; Hayes, D Neil; Liu, Yufeng

    2012-12-01

    Multiple response regression is a useful regression technique to model multiple response variables using the same set of predictor variables. Most existing methods for multiple response regression are designed for modeling homogeneous data. In many applications, however, one may have heterogeneous data where the samples are divided into multiple groups. Our motivating example is a cancer dataset where the samples belong to multiple cancer subtypes. In this paper, we consider modeling the data coming from a mixture of several Gaussian distributions with known group labels. A naive approach is to split the data into several groups according to the labels and model each group separately. Although it is simple, this approach ignores potential common structures across different groups. We propose new penalized methods to model all groups jointly in which the common and unique structures can be identified. The proposed methods estimate the regression coefficient matrix, as well as the conditional inverse covariance matrix of response variables. Asymptotic properties of the proposed methods are explored. Through numerical examples, we demonstrate that both estimation and prediction can be improved by modeling all groups jointly using the proposed methods. An application to a glioblastoma cancer dataset reveals some interesting common and unique gene relationships across different cancer subtypes.

  6. Short-Run Asset Selection using a Logistic Model

    Directory of Open Access Journals (Sweden)

    Walter Gonçalves Junior

    2011-06-01

    Full Text Available Investors constantly look for significant predictors and accurate models to forecast future results, whose occasional efficacy end up being neutralized by market efficiency. Regardless, such predictors are widely used for seeking better (and more unique perceptions. This paper aims to investigate to what extent some of the most notorious indicators have discriminatory power to select stocks, and if it is feasible with such variables to build models that could anticipate those with good performance. In order to do that, logistical regressions were conducted with stocks traded at Bovespa using the selected indicators as explanatory variables. Investigated in this study were the outputs of Bovespa Index, liquidity, the Sharpe Ratio, ROE, MB, size and age evidenced to be significant predictors. Also examined were half-year, logistical models, which were adjusted in order to check the potential acceptable discriminatory power for the asset selection.

  7. A binary logistic regression model with complex sampling design of ...

    African Journals Online (AJOL)

    2017-09-03

    Sep 3, 2017 ... Bi-variable and multi-variable binary logistic regression model with complex sampling design was fitted. .... Data was entered into STATA-12 and analyzed using. SPSS-21. .... lack of access/too far or costs too much. 35. 1.2.

  8. A comparison of random forest regression and multiple linear regression for prediction in neuroscience.

    Science.gov (United States)

    Smith, Paul F; Ganesh, Siva; Liu, Ping

    2013-10-30

    Regression is a common statistical tool for prediction in neuroscience. However, linear regression is by far the most common form of regression used, with regression trees receiving comparatively little attention. In this study, the results of conventional multiple linear regression (MLR) were compared with those of random forest regression (RFR), in the prediction of the concentrations of 9 neurochemicals in the vestibular nucleus complex and cerebellum that are part of the l-arginine biochemical pathway (agmatine, putrescine, spermidine, spermine, l-arginine, l-ornithine, l-citrulline, glutamate and γ-aminobutyric acid (GABA)). The R(2) values for the MLRs were higher than the proportion of variance explained values for the RFRs: 6/9 of them were ≥ 0.70 compared to 4/9 for RFRs. Even the variables that had the lowest R(2) values for the MLRs, e.g. ornithine (0.50) and glutamate (0.61), had much lower proportion of variance explained values for the RFRs (0.27 and 0.49, respectively). The RSE values for the MLRs were lower than those for the RFRs in all but two cases. In general, MLRs seemed to be superior to the RFRs in terms of predictive value and error. In the case of this data set, MLR appeared to be superior to RFR in terms of its explanatory value and error. This result suggests that MLR may have advantages over RFR for prediction in neuroscience with this kind of data set, but that RFR can still have good predictive value in some cases. Copyright © 2013 Elsevier B.V. All rights reserved.

  9. Using Dominance Analysis to Determine Predictor Importance in Logistic Regression

    Science.gov (United States)

    Azen, Razia; Traxel, Nicole

    2009-01-01

    This article proposes an extension of dominance analysis that allows researchers to determine the relative importance of predictors in logistic regression models. Criteria for choosing logistic regression R[superscript 2] analogues were determined and measures were selected that can be used to perform dominance analysis in logistic regression. A…

  10. A Hybrid Approach of Stepwise Regression, Logistic Regression, Support Vector Machine, and Decision Tree for Forecasting Fraudulent Financial Statements

    Directory of Open Access Journals (Sweden)

    Suduan Chen

    2014-01-01

    Full Text Available As the fraudulent financial statement of an enterprise is increasingly serious with each passing day, establishing a valid forecasting fraudulent financial statement model of an enterprise has become an important question for academic research and financial practice. After screening the important variables using the stepwise regression, the study also matches the logistic regression, support vector machine, and decision tree to construct the classification models to make a comparison. The study adopts financial and nonfinancial variables to assist in establishment of the forecasting fraudulent financial statement model. Research objects are the companies to which the fraudulent and nonfraudulent financial statement happened between years 1998 to 2012. The findings are that financial and nonfinancial information are effectively used to distinguish the fraudulent financial statement, and decision tree C5.0 has the best classification effect 85.71%.

  11. Bivariate least squares linear regression: Towards a unified analytic formalism. I. Functional models

    Science.gov (United States)

    Caimmi, R.

    2011-08-01

    Concerning bivariate least squares linear regression, the classical approach pursued for functional models in earlier attempts ( York, 1966, 1969) is reviewed using a new formalism in terms of deviation (matrix) traces which, for unweighted data, reduce to usual quantities leaving aside an unessential (but dimensional) multiplicative factor. Within the framework of classical error models, the dependent variable relates to the independent variable according to the usual additive model. The classes of linear models considered are regression lines in the general case of correlated errors in X and in Y for weighted data, and in the opposite limiting situations of (i) uncorrelated errors in X and in Y, and (ii) completely correlated errors in X and in Y. The special case of (C) generalized orthogonal regression is considered in detail together with well known subcases, namely: (Y) errors in X negligible (ideally null) with respect to errors in Y; (X) errors in Y negligible (ideally null) with respect to errors in X; (O) genuine orthogonal regression; (R) reduced major-axis regression. In the limit of unweighted data, the results determined for functional models are compared with their counterparts related to extreme structural models i.e. the instrumental scatter is negligible (ideally null) with respect to the intrinsic scatter ( Isobe et al., 1990; Feigelson and Babu, 1992). While regression line slope and intercept estimators for functional and structural models necessarily coincide, the contrary holds for related variance estimators even if the residuals obey a Gaussian distribution, with the exception of Y models. An example of astronomical application is considered, concerning the [O/H]-[Fe/H] empirical relations deduced from five samples related to different stars and/or different methods of oxygen abundance determination. For selected samples and assigned methods, different regression models yield consistent results within the errors (∓ σ) for both

  12. Modeling the energy content of combustible ship-scrapping waste at Alang-Sosiya, India, using multiple regression analysis.

    Science.gov (United States)

    Reddy, M Srinivasa; Basha, Shaik; Joshi, H V; Sravan Kumar, V G; Jha, B; Ghosh, P K

    2005-01-01

    Alang-Sosiya is the largest ship-scrapping yard in the world, established in 1982. Every year an average of 171 ships having a mean weight of 2.10 x 10(6)(+/-7.82 x 10(5)) of light dead weight tonnage (LDT) being scrapped. Apart from scrapped metals, this yard generates a massive amount of combustible solid waste in the form of waste wood, plastic, insulation material, paper, glass wool, thermocol pieces (polyurethane foam material), sponge, oiled rope, cotton waste, rubber, etc. In this study multiple regression analysis was used to develop predictive models for energy content of combustible ship-scrapping solid wastes. The scope of work comprised qualitative and quantitative estimation of solid waste samples and performing a sequential selection procedure for isolating variables. Three regression models were developed to correlate the energy content (net calorific values (LHV)) with variables derived from material composition, proximate and ultimate analyses. The performance of these models for this particular waste complies well with the equations developed by other researchers (Dulong, Steuer, Scheurer-Kestner and Bento's) for estimating energy content of municipal solid waste.

  13. Social variables exert selective pressures in the evolution and form of primate mimetic musculature.

    Science.gov (United States)

    Burrows, Anne M; Li, Ly; Waller, Bridget M; Micheletta, Jerome

    2016-04-01

    Mammals use their faces in social interactions more so than any other vertebrates. Primates are an extreme among most mammals in their complex, direct, lifelong social interactions and their frequent use of facial displays is a means of proximate visual communication with conspecifics. The available repertoire of facial displays is primarily controlled by mimetic musculature, the muscles that move the face. The form of these muscles is, in turn, limited by and influenced by phylogenetic inertia but here we use examples, both morphological and physiological, to illustrate the influence that social variables may exert on the evolution and form of mimetic musculature among primates. Ecomorphology is concerned with the adaptive responses of morphology to various ecological variables such as diet, foliage density, predation pressures, and time of day activity. We present evidence that social variables also exert selective pressures on morphology, specifically using mimetic muscles among primates as an example. Social variables include group size, dominance 'style', and mating systems. We present two case studies to illustrate the potential influence of social behavior on adaptive morphology of mimetic musculature in primates: (1) gross morphology of the mimetic muscles around the external ear in closely related species of macaque (Macaca mulatta and Macaca nigra) characterized by varying dominance styles and (2) comparative physiology of the orbicularis oris muscle among select ape species. This muscle is used in both facial displays/expressions and in vocalizations/human speech. We present qualitative observations of myosin fiber-type distribution in this muscle of siamang (Symphalangus syndactylus), chimpanzee (Pan troglodytes), and human to demonstrate the potential influence of visual and auditory communication on muscle physiology. In sum, ecomorphologists should be aware of social selective pressures as well as ecological ones, and that observed morphology might

  14. Effects of carprofen or meloxicam on selected haemostatic variables in miniature pigs after orthopaedic surgery

    Directory of Open Access Journals (Sweden)

    Petr Raušer

    2011-01-01

    Full Text Available The aim of the study was to detect and compare the haemostatic variables and bleeding after 7‑days administration of carprofen or meloxicam in clinically healthy miniature pigs. Twenty-one clinically healthy Göttingen miniature pigs were divided into 3 groups. Selected haemostatic variables such as platelet count, prothrombin time, activated partial thromboplastin time, thrombin time, fibrinogen, serum biochemical variables such as total protein, bilirubin, urea, creatinine, alkaline phosphatase, alanine aminotransferase and gamma-glutamyltransferase and haemoglobin, haematocrit, red blood cells, white blood cells and buccal mucosal bleeding time were assessed before and 7 days after daily intramuscular administration of saline (1.5 ml per animal, control group, carprofen (2 mg·kg-1 or meloxicam (0.1 mg·kg-1. In pigs receiving carprofen or meloxicam, the thrombin time was significantly increased (p p p p < 0.05 compared to the control group. Significant differences were not detected in other haemostatic, biochemical variables or bleeding time compared to other groups or to the pretreatment values. Intramuscular administration of carprofen or meloxicam in healthy miniature pigs for 7 days causes sporadic, but not clinically important changes of selected haemostatic variables. Therefore, we can recommend them for perioperative use, e.g. for their analgesic effects, in orthopaedic or other surgical procedures without increased bleeding.

  15. Locating disease genes using Bayesian variable selection with the Haseman-Elston method

    Directory of Open Access Journals (Sweden)

    He Qimei

    2003-12-01

    Full Text Available Abstract Background We applied stochastic search variable selection (SSVS, a Bayesian model selection method, to the simulated data of Genetic Analysis Workshop 13. We used SSVS with the revisited Haseman-Elston method to find the markers linked to the loci determining change in cholesterol over time. To study gene-gene interaction (epistasis and gene-environment interaction, we adopted prior structures, which incorporate the relationship among the predictors. This allows SSVS to search in the model space more efficiently and avoid the less likely models. Results In applying SSVS, instead of looking at the posterior distribution of each of the candidate models, which is sensitive to the setting of the prior, we ranked the candidate variables (markers according to their marginal posterior probability, which was shown to be more robust to the prior. Compared with traditional methods that consider one marker at a time, our method considers all markers simultaneously and obtains more favorable results. Conclusions We showed that SSVS is a powerful method for identifying linked markers using the Haseman-Elston method, even for weak effects. SSVS is very effective because it does a smart search over the entire model space.

  16. Bayesian variable selection for post-analytic interrogation of susceptibility loci.

    Science.gov (United States)

    Chen, Siying; Nunez, Sara; Reilly, Muredach P; Foulkes, Andrea S

    2017-06-01

    Understanding the complex interplay among protein coding genes and regulatory elements requires rigorous interrogation with analytic tools designed for discerning the relative contributions of overlapping genomic regions. To this aim, we offer a novel application of Bayesian variable selection (BVS) for classifying genomic class level associations using existing large meta-analysis summary level resources. This approach is applied using the expectation maximization variable selection (EMVS) algorithm to typed and imputed SNPs across 502 protein coding genes (PCGs) and 220 long intergenic non-coding RNAs (lncRNAs) that overlap 45 known loci for coronary artery disease (CAD) using publicly available Global Lipids Gentics Consortium (GLGC) (Teslovich et al., 2010; Willer et al., 2013) meta-analysis summary statistics for low-density lipoprotein cholesterol (LDL-C). The analysis reveals 33 PCGs and three lncRNAs across 11 loci with >50% posterior probabilities for inclusion in an additive model of association. The findings are consistent with previous reports, while providing some new insight into the architecture of LDL-cholesterol to be investigated further. As genomic taxonomies continue to evolve, additional classes such as enhancer elements and splicing regions, can easily be layered into the proposed analysis framework. Moreover, application of this approach to alternative publicly available meta-analysis resources, or more generally as a post-analytic strategy to further interrogate regions that are identified through single point analysis, is straightforward. All coding examples are implemented in R version 3.2.1 and provided as supplemental material. © 2016, The International Biometric Society.

  17. The prediction of intelligence in preschool children using alternative models to regression.

    Science.gov (United States)

    Finch, W Holmes; Chang, Mei; Davis, Andrew S; Holden, Jocelyn E; Rothlisberg, Barbara A; McIntosh, David E

    2011-12-01

    Statistical prediction of an outcome variable using multiple independent variables is a common practice in the social and behavioral sciences. For example, neuropsychologists are sometimes called upon to provide predictions of preinjury cognitive functioning for individuals who have suffered a traumatic brain injury. Typically, these predictions are made using standard multiple linear regression models with several demographic variables (e.g., gender, ethnicity, education level) as predictors. Prior research has shown conflicting evidence regarding the ability of such models to provide accurate predictions of outcome variables such as full-scale intelligence (FSIQ) test scores. The present study had two goals: (1) to demonstrate the utility of a set of alternative prediction methods that have been applied extensively in the natural sciences and business but have not been frequently explored in the social sciences and (2) to develop models that can be used to predict premorbid cognitive functioning in preschool children. Predictions of Stanford-Binet 5 FSIQ scores for preschool-aged children is used to compare the performance of a multiple regression model with several of these alternative methods. Results demonstrate that classification and regression trees provided more accurate predictions of FSIQ scores than does the more traditional regression approach. Implications of these results are discussed.

  18. Analysis of the influence of quantile regression model on mainland tourists' service satisfaction performance.

    Science.gov (United States)

    Wang, Wen-Cheng; Cho, Wen-Chien; Chen, Yin-Jen

    2014-01-01

    It is estimated that mainland Chinese tourists travelling to Taiwan can bring annual revenues of 400 billion NTD to the Taiwan economy. Thus, how the Taiwanese Government formulates relevant measures to satisfy both sides is the focus of most concern. Taiwan must improve the facilities and service quality of its tourism industry so as to attract more mainland tourists. This paper conducted a questionnaire survey of mainland tourists and used grey relational analysis in grey mathematics to analyze the satisfaction performance of all satisfaction question items. The first eight satisfaction items were used as independent variables, and the overall satisfaction performance was used as a dependent variable for quantile regression model analysis to discuss the relationship between the dependent variable under different quantiles and independent variables. Finally, this study further discussed the predictive accuracy of the least mean regression model and each quantile regression model, as a reference for research personnel. The analysis results showed that other variables could also affect the overall satisfaction performance of mainland tourists, in addition to occupation and age. The overall predictive accuracy of quantile regression model Q0.25 was higher than that of the other three models.

  19. Analysis of the Influence of Quantile Regression Model on Mainland Tourists' Service Satisfaction Performance

    Science.gov (United States)

    Wang, Wen-Cheng; Cho, Wen-Chien; Chen, Yin-Jen

    2014-01-01

    It is estimated that mainland Chinese tourists travelling to Taiwan can bring annual revenues of 400 billion NTD to the Taiwan economy. Thus, how the Taiwanese Government formulates relevant measures to satisfy both sides is the focus of most concern. Taiwan must improve the facilities and service quality of its tourism industry so as to attract more mainland tourists. This paper conducted a questionnaire survey of mainland tourists and used grey relational analysis in grey mathematics to analyze the satisfaction performance of all satisfaction question items. The first eight satisfaction items were used as independent variables, and the overall satisfaction performance was used as a dependent variable for quantile regression model analysis to discuss the relationship between the dependent variable under different quantiles and independent variables. Finally, this study further discussed the predictive accuracy of the least mean regression model and each quantile regression model, as a reference for research personnel. The analysis results showed that other variables could also affect the overall satisfaction performance of mainland tourists, in addition to occupation and age. The overall predictive accuracy of quantile regression model Q0.25 was higher than that of the other three models. PMID:24574916

  20. Analysis of the Influence of Quantile Regression Model on Mainland Tourists’ Service Satisfaction Performance

    Directory of Open Access Journals (Sweden)

    Wen-Cheng Wang

    2014-01-01

    Full Text Available It is estimated that mainland Chinese tourists travelling to Taiwan can bring annual revenues of 400 billion NTD to the Taiwan economy. Thus, how the Taiwanese Government formulates relevant measures to satisfy both sides is the focus of most concern. Taiwan must improve the facilities and service quality of its tourism industry so as to attract more mainland tourists. This paper conducted a questionnaire survey of mainland tourists and used grey relational analysis in grey mathematics to analyze the satisfaction performance of all satisfaction question items. The first eight satisfaction items were used as independent variables, and the overall satisfaction performance was used as a dependent variable for quantile regression model analysis to discuss the relationship between the dependent variable under different quantiles and independent variables. Finally, this study further discussed the predictive accuracy of the least mean regression model and each quantile regression model, as a reference for research personnel. The analysis results showed that other variables could also affect the overall satisfaction performance of mainland tourists, in addition to occupation and age. The overall predictive accuracy of quantile regression model Q0.25 was higher than that of the other three models.

  1. Network-based group variable selection for detecting expression quantitative trait loci (eQTL

    Directory of Open Access Journals (Sweden)

    Zhang Xuegong

    2011-06-01

    Full Text Available Abstract Background Analysis of expression quantitative trait loci (eQTL aims to identify the genetic loci associated with the expression level of genes. Penalized regression with a proper penalty is suitable for the high-dimensional biological data. Its performance should be enhanced when we incorporate biological knowledge of gene expression network and linkage disequilibrium (LD structure between loci in high-noise background. Results We propose a network-based group variable selection (NGVS method for QTL detection. Our method simultaneously maps highly correlated expression traits sharing the same biological function to marker sets formed by LD. By grouping markers, complex joint activity of multiple SNPs can be considered and the dimensionality of eQTL problem is reduced dramatically. In order to demonstrate the power and flexibility of our method, we used it to analyze two simulations and a mouse obesity and diabetes dataset. We considered the gene co-expression network, grouped markers into marker sets and treated the additive and dominant effect of each locus as a group: as a consequence, we were able to replicate results previously obtained on the mouse linkage dataset. Furthermore, we observed several possible sex-dependent loci and interactions of multiple SNPs. Conclusions The proposed NGVS method is appropriate for problems with high-dimensional data and high-noise background. On eQTL problem it outperforms the classical Lasso method, which does not consider biological knowledge. Introduction of proper gene expression and loci correlation information makes detecting causal markers more accurate. With reasonable model settings, NGVS can lead to novel biological findings.

  2. [Application of negative binomial regression and modified Poisson regression in the research of risk factors for injury frequency].

    Science.gov (United States)

    Cao, Qingqing; Wu, Zhenqiang; Sun, Ying; Wang, Tiezhu; Han, Tengwei; Gu, Chaomei; Sun, Yehuan

    2011-11-01

    To Eexplore the application of negative binomial regression and modified Poisson regression analysis in analyzing the influential factors for injury frequency and the risk factors leading to the increase of injury frequency. 2917 primary and secondary school students were selected from Hefei by cluster random sampling method and surveyed by questionnaire. The data on the count event-based injuries used to fitted modified Poisson regression and negative binomial regression model. The risk factors incurring the increase of unintentional injury frequency for juvenile students was explored, so as to probe the efficiency of these two models in studying the influential factors for injury frequency. The Poisson model existed over-dispersion (P Poisson regression and negative binomial regression model, was fitted better. respectively. Both showed that male gender, younger age, father working outside of the hometown, the level of the guardian being above junior high school and smoking might be the results of higher injury frequencies. On a tendency of clustered frequency data on injury event, both the modified Poisson regression analysis and negative binomial regression analysis can be used. However, based on our data, the modified Poisson regression fitted better and this model could give a more accurate interpretation of relevant factors affecting the frequency of injury.

  3. Capacitance Regression Modelling Analysis on Latex from Selected Rubber Tree Clones

    International Nuclear Information System (INIS)

    Rosli, A D; Baharudin, R; Hashim, H; Khairuzzaman, N A; Mohd Sampian, A F; Abdullah, N E; Kamaru'zzaman, M; Sulaiman, M S

    2015-01-01

    This paper investigates the capacitance regression modelling performance of latex for various rubber tree clones, namely clone 2002, 2008, 2014 and 3001. Conventionally, the rubber tree clones identification are based on observation towards tree features such as shape of leaf, trunk, branching habit and pattern of seeds texture. The former method requires expert persons and very time-consuming. Currently, there is no sensing device based on electrical properties that can be employed to measure different clones from latex samples. Hence, with a hypothesis that the dielectric constant of each clone varies, this paper discusses the development of a capacitance sensor via Capacitance Comparison Bridge (known as capacitance sensor) to measure an output voltage of different latex samples. The proposed sensor is initially tested with 30ml of latex sample prior to gradually addition of dilution water. The output voltage and capacitance obtained from the test are recorded and analyzed using Simple Linear Regression (SLR) model. This work outcome infers that latex clone of 2002 has produced the highest and reliable linear regression line with determination coefficient of 91.24%. In addition, the study also found that the capacitive elements in latex samples deteriorate if it is diluted with higher volume of water. (paper)

  4. Logarithmic Transformations in Regression: Do You Transform Back Correctly?

    Science.gov (United States)

    Dambolena, Ismael G.; Eriksen, Steven E.; Kopcso, David P.

    2009-01-01

    The logarithmic transformation is often used in regression analysis for a variety of purposes such as the linearization of a nonlinear relationship between two or more variables. We have noticed that when this transformation is applied to the response variable, the computation of the point estimate of the conditional mean of the original response…

  5. Spatial variability in levels of benzene, formaldehyde, and total benzene, toluene, ethylbenzene and xylenes in New York City: a land-use regression study

    Directory of Open Access Journals (Sweden)

    Kheirbek Iyad

    2012-07-01

    Full Text Available Abstract Background Hazardous air pollutant exposures are common in urban areas contributing to increased risk of cancer and other adverse health outcomes. While recent analyses indicate that New York City residents experience significantly higher cancer risks attributable to hazardous air pollutant exposures than the United States as a whole, limited data exist to assess intra-urban variability in air toxics exposures. Methods To assess intra-urban spatial variability in exposures to common hazardous air pollutants, street-level air sampling for volatile organic compounds and aldehydes was conducted at 70 sites throughout New York City during the spring of 2011. Land-use regression models were developed using a subset of 59 sites and validated against the remaining 11 sites to describe the relationship between concentrations of benzene, total BTEX (benzene, toluene, ethylbenzene, xylenes and formaldehyde to indicators of local sources, adjusting for temporal variation. Results Total BTEX levels exhibited the most spatial variability, followed by benzene and formaldehyde (coefficient of variation of temporally adjusted measurements of 0.57, 0.35, 0.22, respectively. Total roadway length within 100 m, traffic signal density within 400 m of monitoring sites, and an indicator of temporal variation explained 65% of the total variability in benzene while 70% of the total variability in BTEX was accounted for by traffic signal density within 450 m, density of permitted solvent-use industries within 500 m, and an indicator of temporal variation. Measures of temporal variation, traffic signal density within 400 m, road length within 100 m, and interior building area within 100 m (indicator of heating fuel combustion predicted 83% of the total variability of formaldehyde. The models built with the modeling subset were found to predict concentrations well, predicting 62% to 68% of monitored values at validation sites. Conclusions Traffic and

  6. COMPARISON OF PARTIAL LEAST SQUARES REGRESSION METHOD ALGORITHMS: NIPALS AND PLS-KERNEL AND AN APPLICATION

    Directory of Open Access Journals (Sweden)

    ELİF BULUT

    2013-06-01

    Full Text Available Partial Least Squares Regression (PLSR is a multivariate statistical method that consists of partial least squares and multiple linear regression analysis. Explanatory variables, X, having multicollinearity are reduced to components which explain the great amount of covariance between explanatory and response variable. These components are few in number and they don’t have multicollinearity problem. Then multiple linear regression analysis is applied to those components to model the response variable Y. There are various PLSR algorithms. In this study NIPALS and PLS-Kernel algorithms will be studied and illustrated on a real data set.

  7. QUASI-STELLAR OBJECT SELECTION ALGORITHM USING TIME VARIABILITY AND MACHINE LEARNING: SELECTION OF 1620 QUASI-STELLAR OBJECT CANDIDATES FROM MACHO LARGE MAGELLANIC CLOUD DATABASE

    International Nuclear Information System (INIS)

    Kim, Dae-Won; Protopapas, Pavlos; Alcock, Charles; Trichas, Markos; Byun, Yong-Ik; Khardon, Roni

    2011-01-01

    We present a new quasi-stellar object (QSO) selection algorithm using a Support Vector Machine, a supervised classification method, on a set of extracted time series features including period, amplitude, color, and autocorrelation value. We train a model that separates QSOs from variable stars, non-variable stars, and microlensing events using 58 known QSOs, 1629 variable stars, and 4288 non-variables in the MAssive Compact Halo Object (MACHO) database as a training set. To estimate the efficiency and the accuracy of the model, we perform a cross-validation test using the training set. The test shows that the model correctly identifies ∼80% of known QSOs with a 25% false-positive rate. The majority of the false positives are Be stars. We applied the trained model to the MACHO Large Magellanic Cloud (LMC) data set, which consists of 40 million light curves, and found 1620 QSO candidates. During the selection none of the 33,242 known MACHO variables were misclassified as QSO candidates. In order to estimate the true false-positive rate, we crossmatched the candidates with astronomical catalogs including the Spitzer Surveying the Agents of a Galaxy's Evolution LMC catalog and a few X-ray catalogs. The results further suggest that the majority of the candidates, more than 70%, are QSOs.

  8. Differentiating regressed melanoma from regressed lichenoid keratosis.

    Science.gov (United States)

    Chan, Aegean H; Shulman, Kenneth J; Lee, Bonnie A

    2017-04-01

    Distinguishing regressed lichen planus-like keratosis (LPLK) from regressed melanoma can be difficult on histopathologic examination, potentially resulting in mismanagement of patients. We aimed to identify histopathologic features by which regressed melanoma can be differentiated from regressed LPLK. Twenty actively inflamed LPLK, 12 LPLK with regression and 15 melanomas with regression were compared and evaluated by hematoxylin and eosin staining as well as Melan-A, microphthalmia transcription factor (MiTF) and cytokeratin (AE1/AE3) immunostaining. (1) A total of 40% of regressed melanomas showed complete or near complete loss of melanocytes within the epidermis with Melan-A and MiTF immunostaining, while 8% of regressed LPLK exhibited this finding. (2) Necrotic keratinocytes were seen in the epidermis in 33% regressed melanomas as opposed to all of the regressed LPLK. (3) A dense infiltrate of melanophages in the papillary dermis was seen in 40% of regressed melanomas, a feature not seen in regressed LPLK. In summary, our findings suggest that a complete or near complete loss of melanocytes within the epidermis strongly favors a regressed melanoma over a regressed LPLK. In addition, necrotic epidermal keratinocytes and the presence of a dense band-like distribution of dermal melanophages can be helpful in differentiating these lesions. © 2016 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

  9. Kepler AutoRegressive Planet Search

    Science.gov (United States)

    Caceres, Gabriel Antonio; Feigelson, Eric

    2016-01-01

    The Kepler AutoRegressive Planet Search (KARPS) project uses statistical methodology associated with autoregressive (AR) processes to model Kepler lightcurves in order to improve exoplanet transit detection in systems with high stellar variability. We also introduce a planet-search algorithm to detect transits in time-series residuals after application of the AR models. One of the main obstacles in detecting faint planetary transits is the intrinsic stellar variability of the host star. The variability displayed by many stars may have autoregressive properties, wherein later flux values are correlated with previous ones in some manner. Our analysis procedure consisting of three steps: pre-processing of the data to remove discontinuities, gaps and outliers; AR-type model selection and fitting; and transit signal search of the residuals using a new Transit Comb Filter (TCF) that replaces traditional box-finding algorithms. The analysis procedures of the project are applied to a portion of the publicly available Kepler light curve data for the full 4-year mission duration. Tests of the methods have been made on a subset of Kepler Objects of Interest (KOI) systems, classified both as planetary `candidates' and `false positives' by the Kepler Team, as well as a random sample of unclassified systems. We find that the ARMA-type modeling successfully reduces the stellar variability, by a factor of 10 or more in active stars and by smaller factors in more quiescent stars. A typical quiescent Kepler star has an interquartile range (IQR) of ~10 e-/sec, which may improve slightly after modeling, while those with IQR ranging from 20 to 50 e-/sec, have improvements from 20% up to 70%. High activity stars (IQR exceeding 100) markedly improve. A periodogram based on the TCF is constructed to concentrate the signal of these periodic spikes. When a periodic transit is found, the model is displayed on a standard period-folded averaged light curve. Our findings to date on real

  10. Discriminative Elastic-Net Regularized Linear Regression.

    Science.gov (United States)

    Zhang, Zheng; Lai, Zhihui; Xu, Yong; Shao, Ling; Wu, Jian; Xie, Guo-Sen

    2017-03-01

    In this paper, we aim at learning compact and discriminative linear regression models. Linear regression has been widely used in different problems. However, most of the existing linear regression methods exploit the conventional zero-one matrix as the regression targets, which greatly narrows the flexibility of the regression model. Another major limitation of these methods is that the learned projection matrix fails to precisely project the image features to the target space due to their weak discriminative capability. To this end, we present an elastic-net regularized linear regression (ENLR) framework, and develop two robust linear regression models which possess the following special characteristics. First, our methods exploit two particular strategies to enlarge the margins of different classes by relaxing the strict binary targets into a more feasible variable matrix. Second, a robust elastic-net regularization of singular values is introduced to enhance the compactness and effectiveness of the learned projection matrix. Third, the resulting optimization problem of ENLR has a closed-form solution in each iteration, which can be solved efficiently. Finally, rather than directly exploiting the projection matrix for recognition, our methods employ the transformed features as the new discriminate representations to make final image classification. Compared with the traditional linear regression model and some of its variants, our method is much more accurate in image classification. Extensive experiments conducted on publicly available data sets well demonstrate that the proposed framework can outperform the state-of-the-art methods. The MATLAB codes of our methods can be available at http://www.yongxu.org/lunwen.html.

  11. Density dependence and climate effects in Rocky Mountain elk: an application of regression with instrumental variables for population time series with sampling error.

    Science.gov (United States)

    Creel, Scott; Creel, Michael

    2009-11-01

    1. Sampling error in annual estimates of population size creates two widely recognized problems for the analysis of population growth. First, if sampling error is mistakenly treated as process error, one obtains inflated estimates of the variation in true population trajectories (Staples, Taper & Dennis 2004). Second, treating sampling error as process error is thought to overestimate the importance of density dependence in population growth (Viljugrein et al. 2005; Dennis et al. 2006). 2. In ecology, state-space models are used to account for sampling error when estimating the effects of density and other variables on population growth (Staples et al. 2004; Dennis et al. 2006). In econometrics, regression with instrumental variables is a well-established method that addresses the problem of correlation between regressors and the error term, but requires fewer assumptions than state-space models (Davidson & MacKinnon 1993; Cameron & Trivedi 2005). 3. We used instrumental variables to account for sampling error and fit a generalized linear model to 472 annual observations of population size for 35 Elk Management Units in Montana, from 1928 to 2004. We compared this model with state-space models fit with the likelihood function of Dennis et al. (2006). We discuss the general advantages and disadvantages of each method. Briefly, regression with instrumental variables is valid with fewer distributional assumptions, but state-space models are more efficient when their distributional assumptions are met. 4. Both methods found that population growth was negatively related to population density and winter snow accumulation. Summer rainfall and wolf (Canis lupus) presence had much weaker effects on elk (Cervus elaphus) dynamics [though limitation by wolves is strong in some elk populations with well-established wolf populations (Creel et al. 2007; Creel & Christianson 2008)]. 5. Coupled with predictions for Montana from global and regional climate models, our results

  12. Stochastic weather inputs for improved urban water demand forecasting: application of nonlinear input variable selection and machine learning methods

    Science.gov (United States)

    Quilty, J.; Adamowski, J. F.

    2015-12-01

    Urban water supply systems are often stressed during seasonal outdoor water use as water demands related to the climate are variable in nature making it difficult to optimize the operation of the water supply system. Urban water demand forecasts (UWD) failing to include meteorological conditions as inputs to the forecast model may produce poor forecasts as they cannot account for the increase/decrease in demand related to meteorological conditions. Meteorological records stochastically simulated into the future can be used as inputs to data-driven UWD forecasts generally resulting in improved forecast accuracy. This study aims to produce data-driven UWD forecasts for two different Canadian water utilities (Montreal and Victoria) using machine learning methods by first selecting historical UWD and meteorological records derived from a stochastic weather generator using nonlinear input variable selection. The nonlinear input variable selection methods considered in this work are derived from the concept of conditional mutual information, a nonlinear dependency measure based on (multivariate) probability density functions and accounts for relevancy, conditional relevancy, and redundancy from a potential set of input variables. The results of our study indicate that stochastic weather inputs can improve UWD forecast accuracy for the two sites considered in this work. Nonlinear input variable selection is suggested as a means to identify which meteorological conditions should be utilized in the forecast.

  13. Predicting company growth using logistic regression and neural networks

    Directory of Open Access Journals (Sweden)

    Marijana Zekić-Sušac

    2016-12-01

    Full Text Available The paper aims to establish an efficient model for predicting company growth by leveraging the strengths of logistic regression and neural networks. A real dataset of Croatian companies was used which described the relevant industry sector, financial ratios, income, and assets in the input space, with a dependent binomial variable indicating whether a company had high-growth if it had annualized growth in assets by more than 20% a year over a three-year period. Due to a large number of input variables, factor analysis was performed in the pre -processing stage in order to extract the most important input components. Building an efficient model with a high classification rate and explanatory ability required application of two data mining methods: logistic regression as a parametric and neural networks as a non -parametric method. The methods were tested on the models with and without variable reduction. The classification accuracy of the models was compared using statistical tests and ROC curves. The results showed that neural networks produce a significantly higher classification accuracy in the model when incorporating all available variables. The paper further discusses the advantages and disadvantages of both approaches, i.e. logistic regression and neural networks in modelling company growth. The suggested model is potentially of benefit to investors and economic policy makers as it provides support for recognizing companies with growth potential, especially during times of economic downturn.

  14. Caudal Regression and Encephalocele: Rare Manifestations of Expanded Goldenhar Complex

    Directory of Open Access Journals (Sweden)

    Gabriella D’Angelo

    2017-01-01

    Full Text Available Oculoauriculovertebral spectrum, or Goldenhar Syndrome, is a condition characterized by variable degrees of uni- or bilateral involvement of craniofacial structures, ocular anomalies, and vertebral defects. Its expressivity is variable; therefore, the term “expanded Goldenhar complex” has been coined. The Goldenhar Syndrome usually involves anomalies in craniofacial structures, but it is known that nervous system anomalies, including encephalocele or caudal regression, may, rarely, occur in this condition. We report two rare cases of infants affected by Goldenhar Syndrome, associated with neural tube defects, specifically caudal regression syndrome and nasal encephaloceles, to underline the extremely complex and heterogeneous clinical features of this oculoauriculovertebral spectrum. These additional particular cases could increase the number of new variable spectrums to be included in the “expanded Goldenhar complex.”

  15. Determination of main fruits in adulterated nectars by ATR-FTIR spectroscopy combined with multivariate calibration and variable selection methods.

    Science.gov (United States)

    Miaw, Carolina Sheng Whei; Assis, Camila; Silva, Alessandro Rangel Carolino Sales; Cunha, Maria Luísa; Sena, Marcelo Martins; de Souza, Scheilla Vitorino Carvalho

    2018-07-15

    Grape, orange, peach and passion fruit nectars were formulated and adulterated by dilution with syrup, apple and cashew juices at 10 levels for each adulterant. Attenuated total reflectance Fourier transform mid infrared (ATR-FTIR) spectra were obtained. Partial least squares (PLS) multivariate calibration models allied to different variable selection methods, such as interval partial least squares (iPLS), ordered predictors selection (OPS) and genetic algorithm (GA), were used to quantify the main fruits. PLS improved by iPLS-OPS variable selection showed the highest predictive capacity to quantify the main fruit contents. The selected variables in the final models varied from 72 to 100; the root mean square errors of prediction were estimated from 0.5 to 2.6%; the correlation coefficients of prediction ranged from 0.948 to 0.990; and, the mean relative errors of prediction varied from 3.0 to 6.7%. All of the developed models were validated. Copyright © 2018 Elsevier Ltd. All rights reserved.

  16. LINEAR REGRESSION MODEL ESTİMATİON FOR RIGHT CENSORED DATA

    Directory of Open Access Journals (Sweden)

    Ersin Yılmaz

    2016-05-01

    Full Text Available In this study, firstly we will define a right censored data. If we say shortly right-censored data is censoring values that above the exact line. This may be related with scaling device. And then  we will use response variable acquainted from right-censored explanatory variables. Then the linear regression model will be estimated. For censored data’s existence, Kaplan-Meier weights will be used for  the estimation of the model. With the weights regression model  will be consistent and unbiased with that.   And also there is a method for the censored data that is a semi parametric regression and this method also give  useful results  for censored data too. This study also might be useful for the health studies because of the censored data used in medical issues generally.

  17. The Collinearity Free and Bias Reduced Regression Estimation Project: The Theory of Normalization Ridge Regression. Report No. 2.

    Science.gov (United States)

    Bulcock, J. W.; And Others

    Multicollinearity refers to the presence of highly intercorrelated independent variables in structural equation models, that is, models estimated by using techniques such as least squares regression and maximum likelihood. There is a problem of multicollinearity in both the natural and social sciences where theory formulation and estimation is in…

  18. Considering a non-polynomial basis for local kernel regression problem

    Science.gov (United States)

    Silalahi, Divo Dharma; Midi, Habshah

    2017-01-01

    A common used as solution for local kernel nonparametric regression problem is given using polynomial regression. In this study, we demonstrated the estimator and properties using maximum likelihood estimator for a non-polynomial basis such B-spline to replacing the polynomial basis. This estimator allows for flexibility in the selection of a bandwidth and a knot. The best estimator was selected by finding an optimal bandwidth and knot through minimizing the famous generalized validation function.

  19. Benchmarking the Cost per Person of Mass Treatment for Selected Neglected Tropical Diseases: An Approach Based on Literature Review and Meta-regression with Web-Based Software Application.

    Directory of Open Access Journals (Sweden)

    Christopher Fitzpatrick

    2016-12-01

    Full Text Available Advocacy around mass treatment for the elimination of selected Neglected Tropical Diseases (NTDs has typically put the cost per person treated at less than US$ 0.50. Whilst useful for advocacy, the focus on a single number misrepresents the complexity of delivering "free" donated medicines to about a billion people across the world. We perform a literature review and meta-regression of the cost per person per round of mass treatment against NTDs. We develop a web-based software application (https://healthy.shinyapps.io/benchmark/ to calculate setting-specific unit costs against which programme budgets and expenditures or results-based pay-outs can be benchmarked.We reviewed costing studies of mass treatment for the control, elimination or eradication of lymphatic filariasis, schistosomiasis, soil-transmitted helminthiasis, onchocerciasis, trachoma and yaws. These are the main 6 NTDs for which mass treatment is recommended. We extracted financial and economic unit costs, adjusted to a standard definition and base year. We regressed unit costs on the number of people treated and other explanatory variables. Regression results were used to "predict" country-specific unit cost benchmarks.We reviewed 56 costing studies and included in the meta-regression 34 studies from 23 countries and 91 sites. Unit costs were found to be very sensitive to economies of scale, and the decision of whether or not to use local volunteers. Financial unit costs are expected to be less than 2015 US$ 0.50 in most countries for programmes that treat 100 thousand people or more. However, for smaller programmes, including those in the "last mile", or those that cannot rely on local volunteers, both economic and financial unit costs are expected to be higher.The available evidence confirms that mass treatment offers a low cost public health intervention on the path towards universal health coverage. However, more costing studies focussed on elimination are needed. Unit cost

  20. Gender effects in gaming research: a case for regression residuals?

    Science.gov (United States)

    Pfister, Roland

    2011-10-01

    Numerous recent studies have examined the impact of video gaming on various dependent variables, including the players' affective reactions, positive as well as detrimental cognitive effects, and real-world aggression. These target variables are typically analyzed as a function of game characteristics and player attributes-especially gender. However, findings on the uneven distribution of gaming experience between males and females, on the one hand, and the effect of gaming experience on several target variables, on the other hand, point at a possible confound when gaming experiments are analyzed with a standard analysis of variance. This study uses simulated data to exemplify analysis of regression residuals as a potentially beneficial data analysis strategy for such datasets. As the actual impact of gaming experience on each of the various dependent variables differs, the ultimate benefits of analysis of regression residuals entirely depend on the research question, but it offers a powerful statistical approach to video game research whenever gaming experience is a confounding factor.