NONPARAMETRIC ESTIMATION OF CHARACTERISTICS OF PROBABILITY DISTRIBUTIONS
Directory of Open Access Journals (Sweden)
Orlov A. I.
2015-10-01
Full Text Available The article is devoted to the nonparametric point and interval estimation of the characteristics of the probabilistic distribution (the expectation, median, variance, standard deviation, variation coefficient of the sample results. Sample values are regarded as the implementation of independent and identically distributed random variables with an arbitrary distribution function having the desired number of moments. Nonparametric analysis procedures are compared with the parametric procedures, based on the assumption that the sample values have a normal distribution. Point estimators are constructed in the obvious way - using sample analogs of the theoretical characteristics. Interval estimators are based on asymptotic normality of sample moments and functions from them. Nonparametric asymptotic confidence intervals are obtained through the use of special output technology of the asymptotic relations of Applied Statistics. In the first step this technology uses the multidimensional central limit theorem, applied to the sums of vectors whose coordinates are the degrees of initial random variables. The second step is the conversion limit multivariate normal vector to obtain the interest of researcher vector. At the same considerations we have used linearization and discarded infinitesimal quantities. The third step - a rigorous justification of the results on the asymptotic standard for mathematical and statistical reasoning level. It is usually necessary to use the necessary and sufficient conditions for the inheritance of convergence. This article contains 10 numerical examples. Initial data - information about an operating time of 50 cutting tools to the limit state. Using the methods developed on the assumption of normal distribution, it can lead to noticeably distorted conclusions in a situation where the normality hypothesis failed. Practical recommendations are: for the analysis of real data we should use nonparametric confidence limits
Poage, J. L.
1975-01-01
A sequential nonparametric pattern classification procedure is presented. The method presented is an estimated version of the Wald sequential probability ratio test (SPRT). This method utilizes density function estimates, and the density estimate used is discussed, including a proof of convergence in probability of the estimate to the true density function. The classification procedure proposed makes use of the theory of order statistics, and estimates of the probabilities of misclassification are given. The procedure was tested on discriminating between two classes of Gaussian samples and on discriminating between two kinds of electroencephalogram (EEG) responses.
Nonparametric estimation of population density for line transect sampling using FOURIER series
Crain, B.R.; Burnham, K.P.; Anderson, D.R.; Lake, J.L.
1979-01-01
A nonparametric, robust density estimation method is explored for the analysis of right-angle distances from a transect line to the objects sighted. The method is based on the FOURIER series expansion of a probability density function over an interval. With only mild assumptions, a general population density estimator of wide applicability is obtained.
Fusion of Hard and Soft Information in Nonparametric Density Estimation
2015-06-10
estimation exploiting, in concert, hard and soft information. Although our development, theoretical and numerical, makes no distinction based on sample...Fusion of Hard and Soft Information in Nonparametric Density Estimation∗ Johannes O. Royset Roger J-B Wets Department of Operations Research...univariate density estimation in situations when the sample ( hard information) is supplemented by “soft” information about the random phenomenon. These
The Probability of Exceedance as a Nonparametric Person-Fit Statistic for Tests of Moderate Length
Tendeiro, Jorge N.; Meijer, Rob R.
2013-01-01
To classify an item score pattern as not fitting a nonparametric item response theory (NIRT) model, the probability of exceedance (PE) of an observed response vector x can be determined as the sum of the probabilities of all response vectors that are, at most, as likely as x, conditional on the test
Probability densities and Lévy densities
DEFF Research Database (Denmark)
Barndorff-Nielsen, Ole Eiler
For positive Lévy processes (i.e. subordinators) formulae are derived that express the probability density or the distribution function in terms of power series in time t. The applicability of the results to finance and to turbulence is briefly indicated.......For positive Lévy processes (i.e. subordinators) formulae are derived that express the probability density or the distribution function in terms of power series in time t. The applicability of the results to finance and to turbulence is briefly indicated....
Probability densities and Lévy densities
DEFF Research Database (Denmark)
Barndorff-Nielsen, Ole Eiler
For positive Lévy processes (i.e. subordinators) formulae are derived that express the probability density or the distribution function in terms of power series in time t. The applicability of the results to finance and to turbulence is briefly indicated.......For positive Lévy processes (i.e. subordinators) formulae are derived that express the probability density or the distribution function in terms of power series in time t. The applicability of the results to finance and to turbulence is briefly indicated....
Quantum probability measures and tomographic probability densities
Amosov, GG; Man'ko, [No Value
2004-01-01
Using a simple relation of the Dirac delta-function to generalized the theta-function, the relationship between the tomographic probability approach and the quantum probability measure approach with the description of quantum states is discussed. The quantum state tomogram expressed in terms of the
LSTA, Rawane Samb
2010-01-01
This thesis deals with the nonparametric estimation of density f of the regression error term E of the model Y=m(X)+E, assuming its independence with the covariate X. The difficulty linked to this study is the fact that the regression error E is not observed. In a such setup, it would be unwise, for estimating f, to use a conditional approach based upon the probability distribution function of Y given X. Indeed, this approach is affected by the curse of dimensionality, so that the resulting estimator of the residual term E would have considerably a slow rate of convergence if the dimension of X is very high. Two approaches are proposed in this thesis to avoid the curse of dimensionality. The first approach uses the estimated residuals, while the second integrates a nonparametric conditional density estimator of Y given X. If proceeding so can circumvent the curse of dimensionality, a challenging issue is to evaluate the impact of the estimated residuals on the final estimator of the density f. We will also at...
Takara, K. T.
2015-12-01
This paper describes a non-parametric frequency analysis method for hydrological extreme-value samples with a size larger than 100, verifying the estimation accuracy with a computer intensive statistics (CIS) resampling such as the bootstrap. Probable maximum values are also incorporated into the analysis for extreme events larger than a design level of flood control. Traditional parametric frequency analysis methods of extreme values include the following steps: Step 1: Collecting and checking extreme-value data; Step 2: Enumerating probability distributions that would be fitted well to the data; Step 3: Parameter estimation; Step 4: Testing goodness of fit; Step 5: Checking the variability of quantile (T-year event) estimates by the jackknife resampling method; and Step_6: Selection of the best distribution (final model). The non-parametric method (NPM) proposed here can skip Steps 2, 3, 4 and 6. Comparing traditional parameter methods (PM) with the NPM, this paper shows that PM often underestimates 100-year quantiles for annual maximum rainfall samples with records of more than 100 years. Overestimation examples are also demonstrated. The bootstrap resampling can do bias correction for the NPM and can also give the estimation accuracy as the bootstrap standard error. This NPM has advantages to avoid various difficulties in above-mentioned steps in the traditional PM. Probable maximum events are also incorporated into the NPM as an upper bound of the hydrological variable. Probable maximum precipitation (PMP) and probable maximum flood (PMF) can be a new parameter value combined with the NPM. An idea how to incorporate these values into frequency analysis is proposed for better management of disasters that exceed the design level. The idea stimulates more integrated approach by geoscientists and statisticians as well as encourages practitioners to consider the worst cases of disasters in their disaster management planning and practices.
Kernel bandwidth estimation for non-parametric density estimation: a comparative study
CSIR Research Space (South Africa)
Van der Walt, CM
2013-12-01
Full Text Available We investigate the performance of conventional bandwidth estimators for non-parametric kernel density estimation on a number of representative pattern-recognition tasks, to gain a better understanding of the behaviour of these estimators in high...
Connolly, Brian; Cohen, K Bretonnel; Santel, Daniel; Bayram, Ulya; Pestian, John
2017-08-07
Probabilistic assessments of clinical care are essential for quality care. Yet, machine learning, which supports this care process has been limited to categorical results. To maximize its usefulness, it is important to find novel approaches that calibrate the ML output with a likelihood scale. Current state-of-the-art calibration methods are generally accurate and applicable to many ML models, but improved granularity and accuracy of such methods would increase the information available for clinical decision making. This novel non-parametric Bayesian approach is demonstrated on a variety of data sets, including simulated classifier outputs, biomedical data sets from the University of California, Irvine (UCI) Machine Learning Repository, and a clinical data set built to determine suicide risk from the language of emergency department patients. The method is first demonstrated on support-vector machine (SVM) models, which generally produce well-behaved, well understood scores. The method produces calibrations that are comparable to the state-of-the-art Bayesian Binning in Quantiles (BBQ) method when the SVM models are able to effectively separate cases and controls. However, as the SVM models' ability to discriminate classes decreases, our approach yields more granular and dynamic calibrated probabilities comparing to the BBQ method. Improvements in granularity and range are even more dramatic when the discrimination between the classes is artificially degraded by replacing the SVM model with an ad hoc k-means classifier. The method allows both clinicians and patients to have a more nuanced view of the output of an ML model, allowing better decision making. The method is demonstrated on simulated data, various biomedical data sets and a clinical data set, to which diverse ML methods are applied. Trivially extending the method to (non-ML) clinical scores is also discussed.
Modulation Based on Probability Density Functions
Williams, Glenn L.
2009-01-01
A proposed method of modulating a sinusoidal carrier signal to convey digital information involves the use of histograms representing probability density functions (PDFs) that characterize samples of the signal waveform. The method is based partly on the observation that when a waveform is sampled (whether by analog or digital means) over a time interval at least as long as one half cycle of the waveform, the samples can be sorted by frequency of occurrence, thereby constructing a histogram representing a PDF of the waveform during that time interval.
Comparison of density estimators. [Estimation of probability density functions
Energy Technology Data Exchange (ETDEWEB)
Kao, S.; Monahan, J.F.
1977-09-01
Recent work in the field of probability density estimation has included the introduction of some new methods, such as the polynomial and spline methods and the nearest neighbor method, and the study of asymptotic properties in depth. This earlier work is summarized here. In addition, the computational complexity of the various algorithms is analyzed, as are some simulations. The object is to compare the performance of the various methods in small samples and their sensitivity to change in their parameters, and to attempt to discover at what point a sample is so small that density estimation can no longer be worthwhile. (RWR)
Photo-z Estimation: An Example of Nonparametric Conditional Density Estimation under Selection Bias
Izbicki, Rafael; Freeman, Peter E
2016-01-01
Redshift is a key quantity for inferring cosmological model parameters. In photometric redshift estimation, cosmologists use the coarse data collected from the vast majority of galaxies to predict the redshift of individual galaxies. To properly quantify the uncertainty in the predictions, however, one needs to go beyond standard regression and instead estimate the full conditional density f(z|x) of a galaxy's redshift z given its photometric covariates x. The problem is further complicated by selection bias: usually only the rarest and brightest galaxies have known redshifts, and these galaxies have characteristics and measured covariates that do not necessarily match those of more numerous and dimmer galaxies of unknown redshift. Unfortunately, there is not much research on how to best estimate complex multivariate densities in such settings. Here we describe a general framework for properly constructing and assessing nonparametric conditional density estimators under selection bias, and for combining two o...
Ocampo-Duque, William; Osorio, Carolina; Piamba, Christian; Schuhmacher, Marta; Domingo, José L
2013-02-01
The integration of water quality monitoring variables is essential in environmental decision making. Nowadays, advanced techniques to manage subjectivity, imprecision, uncertainty, vagueness, and variability are required in such complex evaluation process. We here propose a probabilistic fuzzy hybrid model to assess river water quality. Fuzzy logic reasoning has been used to compute a water quality integrative index. By applying a Monte Carlo technique, based on non-parametric probability distributions, the randomness of model inputs was estimated. Annual histograms of nine water quality variables were built with monitoring data systematically collected in the Colombian Cauca River, and probability density estimations using the kernel smoothing method were applied to fit data. Several years were assessed, and river sectors upstream and downstream the city of Santiago de Cali, a big city with basic wastewater treatment and high industrial activity, were analyzed. The probabilistic fuzzy water quality index was able to explain the reduction in water quality, as the river receives a larger number of agriculture, domestic, and industrial effluents. The results of the hybrid model were compared to traditional water quality indexes. The main advantage of the proposed method is that it considers flexible boundaries between the linguistic qualifiers used to define the water status, being the belongingness of water quality to the diverse output fuzzy sets or classes provided with percentiles and histograms, which allows classify better the real water condition. The results of this study show that fuzzy inference systems integrated to stochastic non-parametric techniques may be used as complementary tools in water quality indexing methodologies.
Carroll, Raymond J.
2011-03-01
In many applications we can expect that, or are interested to know if, a density function or a regression curve satisfies some specific shape constraints. For example, when the explanatory variable, X, represents the value taken by a treatment or dosage, the conditional mean of the response, Y , is often anticipated to be a monotone function of X. Indeed, if this regression mean is not monotone (in the appropriate direction) then the medical or commercial value of the treatment is likely to be significantly curtailed, at least for values of X that lie beyond the point at which monotonicity fails. In the case of a density, common shape constraints include log-concavity and unimodality. If we can correctly guess the shape of a curve, then nonparametric estimators can be improved by taking this information into account. Addressing such problems requires a method for testing the hypothesis that the curve of interest satisfies a shape constraint, and, if the conclusion of the test is positive, a technique for estimating the curve subject to the constraint. Nonparametric methodology for solving these problems already exists, but only in cases where the covariates are observed precisely. However in many problems, data can only be observed with measurement errors, and the methods employed in the error-free case typically do not carry over to this error context. In this paper we develop a novel approach to hypothesis testing and function estimation under shape constraints, which is valid in the context of measurement errors. Our method is based on tilting an estimator of the density or the regression mean until it satisfies the shape constraint, and we take as our test statistic the distance through which it is tilted. Bootstrap methods are used to calibrate the test. The constrained curve estimators that we develop are also based on tilting, and in that context our work has points of contact with methodology in the error-free case.
2013-03-01
Mendenhall , and Sheaffer [25]. For the remainder of this paper, however, we will make use of the Wilcoxon rank sum test for purposes of comparison with the...B. W. Silverman, Density Estimation for Statistics and Data Analysis, Chapman & Hall/CRC, 1986, p. 48. [25] D. D. Wackerly, W. Mendenhall III and R
Unification of Field Theory and Maximum Entropy Methods for Learning Probability Densities
Kinney, Justin B
2014-01-01
Bayesian field theory and maximum entropy are two methods for learning smooth probability distributions (a.k.a. probability densities) from finite sampled data. Both methods were inspired by statistical physics, but the relationship between them has remained unclear. Here I show that Bayesian field theory subsumes maximum entropy density estimation. In particular, the most common maximum entropy methods are shown to be limiting cases of Bayesian inference using field theory priors that impose no boundary conditions on candidate densities. This unification provides a natural way to test the validity of the maximum entropy assumption on one's data. It also provides a better-fitting nonparametric density estimate when the maximum entropy assumption is rejected.
[Use of nonparametric methods in medicine. V. A probability test using iteration].
Gerylovová, A; Holcík, J
1990-10-01
The authors give an account of the so-called Wald-Wolfowitz test of iteration of two types of elements by means of which it is possible to test the probability of the pattern of two types of elements. To facilitate the application of the test five percent critical values are given for the number of iterations for left-sided, right-sided and bilateral alternative hypotheses. The authors present also tables of critical values for up and down iterations which are obtained when we replace the originally assessed sequence of observations by a sequence +1 and -1, depending on the sign of the consecutive differences. The application of the above tests is illustrated on examples.
Randomness as an Equilibrium. Potential and Probability Density
2002-01-01
Randomness is viewed through an analogy between a physical quantity, density of gas, and a mathematical construct -- probability density. Boltzmann's deduction of equilibrium distribution of ideal gas placed in an external potential field than provides a way of viewing probability density from a perspective of forces/potentials, hidden behind it.
Wang, Ying; Wu, Fengchang; Giesy, John P; Feng, Chenglian; Liu, Yuedan; Qin, Ning; Zhao, Yujie
2015-09-01
Due to use of different parametric models for establishing species sensitivity distributions (SSDs), comparison of water quality criteria (WQC) for metals of the same group or period in the periodic table is uncertain and results can be biased. To address this inadequacy, a new probabilistic model, based on non-parametric kernel density estimation was developed and optimal bandwidths and testing methods are proposed. Zinc (Zn), cadmium (Cd), and mercury (Hg) of group IIB of the periodic table are widespread in aquatic environments, mostly at small concentrations, but can exert detrimental effects on aquatic life and human health. With these metals as target compounds, the non-parametric kernel density estimation method and several conventional parametric density estimation methods were used to derive acute WQC of metals for protection of aquatic species in China that were compared and contrasted with WQC for other jurisdictions. HC5 values for protection of different types of species were derived for three metals by use of non-parametric kernel density estimation. The newly developed probabilistic model was superior to conventional parametric density estimations for constructing SSDs and for deriving WQC for these metals. HC5 values for the three metals were inversely proportional to atomic number, which means that the heavier atoms were more potent toxicants. The proposed method provides a novel alternative approach for developing SSDs that could have wide application prospects in deriving WQC and use in assessment of risks to ecosystems.
Hilbert Space of Probability Density Functions Based on Aitchison Geometry
Institute of Scientific and Technical Information of China (English)
J. J. EGOZCUE; J. L. D(I)AZ-BARRERO; V. PAWLOWSKY-GLAHN
2006-01-01
The set of probability functions is a convex subset of L1 and it does not have a linear space structure when using ordinary sum and multiplication by real constants. Moreover, difficulties arise when dealing with distances between densities. The crucial point is that usual distances are not invariant under relevant transformations of densities. To overcome these limitations, Aitchison's ideas on compositional data analysis are used, generalizing perturbation and power transformation, as well as the Aitchison inner product, to operations on probability density functions with support on a finite interval. With these operations at hand, it is shown that the set of bounded probability density functions on finite intervals is a pre-Hilbert space. A Hilbert space of densities, whose logarithm is square-integrable, is obtained as the natural completion of the pre-Hilbert space.
Low default credit scoring using two-class non-parametric kernel density estimation
CSIR Research Space (South Africa)
Rademeyer, E
2016-12-01
Full Text Available This paper investigates the performance of two-class classification credit scoring data sets with low default ratios. The standard two-class parametric Gaussian and non-parametric Parzen classifiers are extended, using Bayes’ rule, to include either...
Failure Analysis of Wind Turbines by Probability Density Evolution Method
DEFF Research Database (Denmark)
Sichani, Mahdi Teimouri; Nielsen, Søren R.K.; Liu, W.F.
2013-01-01
The aim of this study is to present an efficient and accurate method for estimation of the failure probability of wind turbine structures which work under turbulent wind load. The classical method for this is to fit one of the extreme value probability distribution functions to the extracted maxima....... This is not practical due to its excessive computational load. This problem can alternatively be tackled if the evolution of the probability density function (PDF) of the response process can be realized. The evolutionary PDF can then be integrated on the boundaries of the problem. For this reason we propose to use...... the Probability Density Evolution Method (PDEM). PDEM can alternatively be used to obtain the distribution of the extreme values of the response process by simulation. This approach requires less computational effort than integrating the evolution of the PDF; but may be less accurate. In this paper we present...
A Probability Density Function for Neutrino Masses and Mixings
Fortin, Jean-François; Marleau, Luc
2016-01-01
The anarchy principle leading to the see-saw ensemble is studied analytically with the usual tools of random matrix theory. The probability density function for the see-saw ensemble of $N\\times N$ matrices is obtained in terms of a multidimensional integral. This integral involves all light neutrino masses, leading to a complicated probability density function. It is shown that the probability density function for the neutrino mixing angles and phases is the appropriate Haar measure. The decoupling of the light neutrino masses and neutrino mixings implies no correlation between the neutrino mass eigenstates and the neutrino mixing matrix, in contradiction with observations but in agreement with some of the claims found in the literature.
Probability density function for neutrino masses and mixings
Fortin, Jean-François; Giasson, Nicolas; Marleau, Luc
2016-12-01
The anarchy principle leading to the seesaw ensemble is studied analytically with the usual tools of random matrix theory. The probability density function for the seesaw ensemble of N ×N matrices is obtained in terms of a multidimensional integral. This integral involves all light neutrino masses, leading to a complicated probability density function. It is shown that the probability density function for the neutrino mixing angles and phases is the appropriate Haar measure. The decoupling of the light neutrino masses and neutrino mixings implies no correlation between the neutrino mass eigenstates and the neutrino mixing matrix and leads to a loss of predictive power when comparing with observations. This decoupling is in agreement with some of the claims found in the literature.
Probability density function modeling for sub-powered interconnects
Pater, Flavius; Amaricǎi, Alexandru
2016-06-01
This paper proposes three mathematical models for reliability probability density function modeling the interconnect supplied at sub-threshold voltages: spline curve approximations, Gaussian models,and sine interpolation. The proposed analysis aims at determining the most appropriate fitting for the switching delay - probability of correct switching for sub-powered interconnects. We compare the three mathematical models with the Monte-Carlo simulations of interconnects for 45 nm CMOS technology supplied at 0.25V.
An homotopy of isometries related to a probability density
Groux, Roland
2011-01-01
We are studying here a family of probability density functions indexed by a real parameter, and constructed from homographic relations between associated Stieltjes transforms. From the analysis of orthogonal polynomials we deduce a family of isometries in relation to the classical operators creating secondary polynomials and we give an application to the explicit resolution of specific integral equations.
Visualization techniques for spatial probability density function data
Directory of Open Access Journals (Sweden)
Udeepta D Bordoloi
2006-01-01
Full Text Available Novel visualization methods are presented for spatial probability density function data. These are spatial datasets, where each pixel is a random variable, and has multiple samples which are the results of experiments on that random variable. We use clustering as a means to reduce the information contained in these datasets; and present two different ways of interpreting and clustering the data. The clustering methods are used on two datasets, and the results are discussed with the help of visualization techniques designed for the spatial probability data.
Estimation of probability densities using scale-free field theories.
Kinney, Justin B
2014-07-01
The question of how best to estimate a continuous probability density from finite data is an intriguing open problem at the interface of statistics and physics. Previous work has argued that this problem can be addressed in a natural way using methods from statistical field theory. Here I describe results that allow this field-theoretic approach to be rapidly and deterministically computed in low dimensions, making it practical for use in day-to-day data analysis. Importantly, this approach does not impose a privileged length scale for smoothness of the inferred probability density, but rather learns a natural length scale from the data due to the tradeoff between goodness of fit and an Occam factor. Open source software implementing this method in one and two dimensions is provided.
Probability distribution functions in the finite density lattice QCD
Ejiri, S; Aoki, S; Kanaya, K; Saito, H; Hatsuda, T; Ohno, H; Umeda, T
2012-01-01
We study the phase structure of QCD at high temperature and density by lattice QCD simulations adopting a histogram method. We try to solve the problems which arise in the numerical study of the finite density QCD, focusing on the probability distribution function (histogram). As a first step, we investigate the quark mass dependence and the chemical potential dependence of the probability distribution function as a function of the Polyakov loop when all quark masses are sufficiently large, and study the properties of the distribution function. The effect from the complex phase of the quark determinant is estimated explicitly. The shape of the distribution function changes with the quark mass and the chemical potential. Through the shape of the distribution, the critical surface which separates the first order transition and crossover regions in the heavy quark region is determined for the 2+1-flavor case.
Probability density functions of instantaneous Stokes parameters on weak scattering
Chen, Xi; Korotkova, Olga
2017-10-01
The single-point probability density functions (PDF) of the instantaneous Stokes parameters of a polarized plane-wave light field scattered from a three-dimensional, statistically stationary, weak medium with Gaussian statistics and Gaussian correlation function have been studied for the first time. Apart from the scattering geometry the PDF distributions of the scattered light have been related to the illumination's polarization state and the correlation properties of the medium.
Fast and accurate probability density estimation in large high dimensional astronomical datasets
Gupta, Pramod; Connolly, Andrew J.; Gardner, Jeffrey P.
2015-01-01
Astronomical surveys will generate measurements of hundreds of attributes (e.g. color, size, shape) on hundreds of millions of sources. Analyzing these large, high dimensional data sets will require efficient algorithms for data analysis. An example of this is probability density estimation that is at the heart of many classification problems such as the separation of stars and quasars based on their colors. Popular density estimation techniques use binning or kernel density estimation. Kernel density estimation has a small memory footprint but often requires large computational resources. Binning has small computational requirements but usually binning is implemented with multi-dimensional arrays which leads to memory requirements which scale exponentially with the number of dimensions. Hence both techniques do not scale well to large data sets in high dimensions. We present an alternative approach of binning implemented with hash tables (BASH tables). This approach uses the sparseness of data in the high dimensional space to ensure that the memory requirements are small. However hashing requires some extra computation so a priori it is not clear if the reduction in memory requirements will lead to increased computational requirements. Through an implementation of BASH tables in C++ we show that the additional computational requirements of hashing are negligible. Hence this approach has small memory and computational requirements. We apply our density estimation technique to photometric selection of quasars using non-parametric Bayesian classification and show that the accuracy of the classification is same as the accuracy of earlier approaches. Since the BASH table approach is one to three orders of magnitude faster than the earlier approaches it may be useful in various other applications of density estimation in astrostatistics.
Quantal Response: Nonparametric Modeling
2017-01-01
spline N−spline Fig. 3 Logistic regression 7 Approved for public release; distribution is unlimited. 5. Nonparametric QR Models Nonparametric linear ...stimulus and probability of response. The Generalized Linear Model approach does not make use of the limit distribution but allows arbitrary functional...7. Conclusions and Recommendations 18 8. References 19 Appendix A. The Linear Model 21 Appendix B. The Generalized Linear Model 33 Appendix C. B
Continuation of probability density functions using a generalized Lyapunov approach
Energy Technology Data Exchange (ETDEWEB)
Baars, S., E-mail: s.baars@rug.nl [Johann Bernoulli Institute for Mathematics and Computer Science, University of Groningen, P.O. Box 407, 9700 AK Groningen (Netherlands); Viebahn, J.P., E-mail: viebahn@cwi.nl [Centrum Wiskunde & Informatica (CWI), P.O. Box 94079, 1090 GB, Amsterdam (Netherlands); Mulder, T.E., E-mail: t.e.mulder@uu.nl [Institute for Marine and Atmospheric research Utrecht, Department of Physics and Astronomy, Utrecht University, Princetonplein 5, 3584 CC Utrecht (Netherlands); Kuehn, C., E-mail: ckuehn@ma.tum.de [Technical University of Munich, Faculty of Mathematics, Boltzmannstr. 3, 85748 Garching bei München (Germany); Wubs, F.W., E-mail: f.w.wubs@rug.nl [Johann Bernoulli Institute for Mathematics and Computer Science, University of Groningen, P.O. Box 407, 9700 AK Groningen (Netherlands); Dijkstra, H.A., E-mail: h.a.dijkstra@uu.nl [Institute for Marine and Atmospheric research Utrecht, Department of Physics and Astronomy, Utrecht University, Princetonplein 5, 3584 CC Utrecht (Netherlands); School of Chemical and Biomolecular Engineering, Cornell University, Ithaca, NY (United States)
2017-05-01
Techniques from numerical bifurcation theory are very useful to study transitions between steady fluid flow patterns and the instabilities involved. Here, we provide computational methodology to use parameter continuation in determining probability density functions of systems of stochastic partial differential equations near fixed points, under a small noise approximation. Key innovation is the efficient solution of a generalized Lyapunov equation using an iterative method involving low-rank approximations. We apply and illustrate the capabilities of the method using a problem in physical oceanography, i.e. the occurrence of multiple steady states of the Atlantic Ocean circulation.
Vehicle Detection Based on Probability Hypothesis Density Filter
Directory of Open Access Journals (Sweden)
Feihu Zhang
2016-04-01
Full Text Available In the past decade, the developments of vehicle detection have been significantly improved. By utilizing cameras, vehicles can be detected in the Regions of Interest (ROI in complex environments. However, vision techniques often suffer from false positives and limited field of view. In this paper, a LiDAR based vehicle detection approach is proposed by using the Probability Hypothesis Density (PHD filter. The proposed approach consists of two phases: the hypothesis generation phase to detect potential objects and the hypothesis verification phase to classify objects. The performance of the proposed approach is evaluated in complex scenarios, compared with the state-of-the-art.
INTERACTIVE VISUALIZATION OF PROBABILITY AND CUMULATIVE DENSITY FUNCTIONS
Potter, Kristin
2012-01-01
The probability density function (PDF), and its corresponding cumulative density function (CDF), provide direct statistical insight into the characterization of a random process or field. Typically displayed as a histogram, one can infer probabilities of the occurrence of particular events. When examining a field over some two-dimensional domain in which at each point a PDF of the function values is available, it is challenging to assess the global (stochastic) features present within the field. In this paper, we present a visualization system that allows the user to examine two-dimensional data sets in which PDF (or CDF) information is available at any position within the domain. The tool provides a contour display showing the normed difference between the PDFs and an ansatz PDF selected by the user and, furthermore, allows the user to interactively examine the PDF at any particular position. Canonical examples of the tool are provided to help guide the reader into the mapping of stochastic information to visual cues along with a description of the use of the tool for examining data generated from an uncertainty quantification exercise accomplished within the field of electrophysiology.
de Uña-Álvarez, Jacobo; Meira-Machado, Luís
2015-06-01
Multi-state models are often used for modeling complex event history data. In these models the estimation of the transition probabilities is of particular interest, since they allow for long-term predictions of the process. These quantities have been traditionally estimated by the Aalen-Johansen estimator, which is consistent if the process is Markov. Several non-Markov estimators have been proposed in the recent literature, and their superiority with respect to the Aalen-Johansen estimator has been proved in situations in which the Markov condition is strongly violated. However, the existing estimators have the drawback of requiring that the support of the censoring distribution contains the support of the lifetime distribution, which is not often the case. In this article, we propose two new methods for estimating the transition probabilities in the progressive illness-death model. Some asymptotic results are derived. The proposed estimators are consistent regardless the Markov condition and the referred assumption about the censoring support. We explore the finite sample behavior of the estimators through simulations. The main conclusion of this piece of research is that the proposed estimators are much more efficient than the existing non-Markov estimators in most cases. An application to a clinical trial on colon cancer is included. Extensions to progressive processes beyond the three-state illness-death model are discussed.
Nonparametric estimate of spectral density functions of sample covariance matrices: A first step
2012-01-01
The density function of the limiting spectral distribution of general sample covariance matrices is usually unknown. We propose to use kernel estimators which are proved to be consistent. A simulation study is also conducted to show the performance of the estimators.
Probability Density and CFAR Threshold Estimation for Hyperspectral Imaging
Energy Technology Data Exchange (ETDEWEB)
Clark, G A
2004-09-21
The work reported here shows the proof of principle (using a small data set) for a suite of algorithms designed to estimate the probability density function of hyperspectral background data and compute the appropriate Constant False Alarm Rate (CFAR) matched filter decision threshold for a chemical plume detector. Future work will provide a thorough demonstration of the algorithms and their performance with a large data set. The LASI (Large Aperture Search Initiative) Project involves instrumentation and image processing for hyperspectral images of chemical plumes in the atmosphere. The work reported here involves research and development on algorithms for reducing the false alarm rate in chemical plume detection and identification algorithms operating on hyperspectral image cubes. The chemical plume detection algorithms to date have used matched filters designed using generalized maximum likelihood ratio hypothesis testing algorithms [1, 2, 5, 6, 7, 12, 10, 11, 13]. One of the key challenges in hyperspectral imaging research is the high false alarm rate that often results from the plume detector [1, 2]. The overall goal of this work is to extend the classical matched filter detector to apply Constant False Alarm Rate (CFAR) methods to reduce the false alarm rate, or Probability of False Alarm P{sub FA} of the matched filter [4, 8, 9, 12]. A detector designer is interested in minimizing the probability of false alarm while simultaneously maximizing the probability of detection P{sub D}. This is summarized by the Receiver Operating Characteristic Curve (ROC) [10, 11], which is actually a family of curves depicting P{sub D} vs. P{sub FA}parameterized by varying levels of signal to noise (or clutter) ratio (SNR or SCR). Often, it is advantageous to be able to specify a desired P{sub FA} and develop a ROC curve (P{sub D} vs. decision threshold r{sub 0}) for that case. That is the purpose of this work. Specifically, this work develops a set of algorithms and MATLAB
Lennox, Kristin P; Dahl, David B; Vannucci, Marina; Tsai, Jerry W
2009-06-01
Interest in predicting protein backbone conformational angles has prompted the development of modeling and inference procedures for bivariate angular distributions. We present a Bayesian approach to density estimation for bivariate angular data that uses a Dirichlet process mixture model and a bivariate von Mises distribution. We derive the necessary full conditional distributions to fit the model, as well as the details for sampling from the posterior predictive distribution. We show how our density estimation method makes it possible to improve current approaches for protein structure prediction by comparing the performance of the so-called "whole" and "half" position distributions. Current methods in the field are based on whole position distributions, as density estimation for the half positions requires techniques, such as ours, that can provide good estimates for small datasets. With our method we are able to demonstrate that half position data provides a better approximation for the distribution of conformational angles at a given sequence position, therefore providing increased efficiency and accuracy in structure prediction.
Accurate photometric redshift probability density estimation - method comparison and application
Rau, Markus Michael; Brimioulle, Fabrice; Frank, Eibe; Friedrich, Oliver; Gruen, Daniel; Hoyle, Ben
2015-01-01
We introduce an ordinal classification algorithm for photometric redshift estimation, which vastly improves the reconstruction of photometric redshift probability density functions (PDFs) for individual galaxies and galaxy samples. As a use case we apply our method to CFHTLS galaxies. The ordinal classification algorithm treats distinct redshift bins as ordered values, which improves the quality of photometric redshift PDFs, compared with non-ordinal classification architectures. We also propose a new single value point estimate of the galaxy redshift, that can be used to estimate the full redshift PDF of a galaxy sample. This method is competitive in terms of accuracy with contemporary algorithms, which stack the full redshift PDFs of all galaxies in the sample, but requires orders of magnitudes less storage space. The methods described in this paper greatly improve the log-likelihood of individual object redshift PDFs, when compared with a popular Neural Network code (ANNz). In our use case, this improvemen...
Sueiro, Manuel J.; Abad, Francisco J.
2011-01-01
The distance between nonparametric and parametric item characteristic curves has been proposed as an index of goodness of fit in item response theory in the form of a root integrated squared error index. This article proposes to use the posterior distribution of the latent trait as the nonparametric model and compares the performance of an index…
Wang, Ying; Feng, Chenglian; Liu, Yuedan; Zhao, Yujie; Li, Huixian; Zhao, Tianhui; Guo, Wenjing
2017-02-01
Transition metals in the fourth period of the periodic table of the elements are widely widespread in aquatic environments. They could often occur at certain concentrations to cause adverse effects on aquatic life and human health. Generally, parametric models are mostly used to construct species sensitivity distributions (SSDs), which result in comparison for water quality criteria (WQC) of elements in the same period or group of the periodic table might be inaccurate and the results could be biased. To address this inadequacy, the non-parametric kernel density estimation (NPKDE) with its optimal bandwidths and testing methods were developed for establishing SSDs. The NPKDE was better fit, more robustness and better predicted than conventional normal and logistic parametric density estimations for constructing SSDs and deriving acute HC5 and WQC for transition metals in the fourth period of the periodic table. The decreasing sequence of HC5 values for the transition metals in the fourth period was Ti > Mn > V > Ni > Zn > Cu > Fe > Co > Cr(VI), which were not proportional to atomic number in the periodic table, and for different metals the relatively sensitive species were also different. The results indicated that except for physical and chemical properties there are other factors affecting toxicity mechanisms of transition metals. The proposed method enriched the methodological foundation for WQC. Meanwhile, it also provided a relatively innovative, accurate approach for the WQC derivation and risk assessment of the same group and period metals in aquatic environments to support protection of aquatic organisms.
Numerical methods for high-dimensional probability density function equations
Cho, H.; Venturi, D.; Karniadakis, G. E.
2016-01-01
In this paper we address the problem of computing the numerical solution to kinetic partial differential equations involving many phase variables. These types of equations arise naturally in many different areas of mathematical physics, e.g., in particle systems (Liouville and Boltzmann equations), stochastic dynamical systems (Fokker-Planck and Dostupov-Pugachev equations), random wave theory (Malakhov-Saichev equations) and coarse-grained stochastic systems (Mori-Zwanzig equations). We propose three different classes of new algorithms addressing high-dimensionality: The first one is based on separated series expansions resulting in a sequence of low-dimensional problems that can be solved recursively and in parallel by using alternating direction methods. The second class of algorithms relies on truncation of interaction in low-orders that resembles the Bogoliubov-Born-Green-Kirkwood-Yvon (BBGKY) framework of kinetic gas theory and it yields a hierarchy of coupled probability density function equations. The third class of algorithms is based on high-dimensional model representations, e.g., the ANOVA method and probabilistic collocation methods. A common feature of all these approaches is that they are reducible to the problem of computing the solution to high-dimensional equations via a sequence of low-dimensional problems. The effectiveness of the new algorithms is demonstrated in numerical examples involving nonlinear stochastic dynamical systems and partial differential equations, with up to 120 variables.
Parameterizing deep convection using the assumed probability density function method
Directory of Open Access Journals (Sweden)
R. L. Storer
2014-06-01
Full Text Available Due to their coarse horizontal resolution, present-day climate models must parameterize deep convection. This paper presents single-column simulations of deep convection using a probability density function (PDF parameterization. The PDF parameterization predicts the PDF of subgrid variability of turbulence, clouds, and hydrometeors. That variability is interfaced to a prognostic microphysics scheme using a Monte Carlo sampling method. The PDF parameterization is used to simulate tropical deep convection, the transition from shallow to deep convection over land, and mid-latitude deep convection. These parameterized single-column simulations are compared with 3-D reference simulations. The agreement is satisfactory except when the convective forcing is weak. The same PDF parameterization is also used to simulate shallow cumulus and stratocumulus layers. The PDF method is sufficiently general to adequately simulate these five deep, shallow, and stratiform cloud cases with a single equation set. This raises hopes that it may be possible in the future, with further refinements at coarse time step and grid spacing, to parameterize all cloud types in a large-scale model in a unified way.
Numerical methods for high-dimensional probability density function equations
Energy Technology Data Exchange (ETDEWEB)
Cho, H. [Department of Mathematics, University of Maryland College Park, College Park, MD 20742 (United States); Venturi, D. [Department of Applied Mathematics and Statistics, University of California Santa Cruz, Santa Cruz, CA 95064 (United States); Karniadakis, G.E., E-mail: gk@dam.brown.edu [Division of Applied Mathematics, Brown University, Providence, RI 02912 (United States)
2016-01-15
In this paper we address the problem of computing the numerical solution to kinetic partial differential equations involving many phase variables. These types of equations arise naturally in many different areas of mathematical physics, e.g., in particle systems (Liouville and Boltzmann equations), stochastic dynamical systems (Fokker–Planck and Dostupov–Pugachev equations), random wave theory (Malakhov–Saichev equations) and coarse-grained stochastic systems (Mori–Zwanzig equations). We propose three different classes of new algorithms addressing high-dimensionality: The first one is based on separated series expansions resulting in a sequence of low-dimensional problems that can be solved recursively and in parallel by using alternating direction methods. The second class of algorithms relies on truncation of interaction in low-orders that resembles the Bogoliubov–Born–Green–Kirkwood–Yvon (BBGKY) framework of kinetic gas theory and it yields a hierarchy of coupled probability density function equations. The third class of algorithms is based on high-dimensional model representations, e.g., the ANOVA method and probabilistic collocation methods. A common feature of all these approaches is that they are reducible to the problem of computing the solution to high-dimensional equations via a sequence of low-dimensional problems. The effectiveness of the new algorithms is demonstrated in numerical examples involving nonlinear stochastic dynamical systems and partial differential equations, with up to 120 variables.
Interpolation of probability densities in ENDF and ENDL
Energy Technology Data Exchange (ETDEWEB)
Hedstrom, G
2006-01-27
Suppose that we are given two probability densities p{sub 0}(E{prime}) and p{sub 1}(E{prime}) for the energy E{prime} of an outgoing particle, p{sub 0}(E{prime}) corresponding to energy E{sub 0} of the incident particle and p{sub 1}(E{prime}) corresponding to incident energy E{sub 1}. If E{sub 0} < E{sub 1}, the problem is how to define p{sub {alpha}}(E{prime}) for intermediate incident energies E{sub {alpha}} = (1 - {alpha})E{sub 0} + {alpha}E{sub 1} with 0 < {alpha} < 1. In this note the author considers three ways to do it. They begin with unit-base interpolation, which is standard in ENDL and is sometimes used in ENDF. They then describe the equiprobable bins used by some Monte Carlo codes. They then close with a discussion of interpolation by corresponding-points, which is commonly used in ENDF.
Efficiency issues related to probability density function comparison
Energy Technology Data Exchange (ETDEWEB)
Kelly, P.M.; Cannon, M.; Barros, J.E.
1996-03-01
The CANDID project (Comparison Algorithm for Navigating Digital Image Databases) employs probability density functions (PDFs) of localized feature information to represent the content of an image for search and retrieval purposes. A similarity measure between PDFs is used to identify database images that are similar to a user-provided query image. Unfortunately, signature comparison involving PDFs is a very time-consuming operation. In this paper, we look into some efficiency considerations when working with PDFS. Since PDFs can take on many forms, we look into tradeoffs between accurate representation and efficiency of manipulation for several data sets. In particular, we typically represent each PDF as a Gaussian mixture (e.g. as a weighted sum of Gaussian kernels) in the feature space. We find that by constraining all Gaussian kernels to have principal axes that are aligned to the natural axes of the feature space, computations involving these PDFs are simplified. We can also constrain the Gaussian kernels to be hyperspherical rather than hyperellipsoidal, simplifying computations even further, and yielding an order of magnitude speedup in signature comparison. This paper illustrates the tradeoffs encountered when using these constraints.
Interactive design of probability density functions for shape grammars
Dang, Minh
2015-11-02
A shape grammar defines a procedural shape space containing a variety of models of the same class, e.g. buildings, trees, furniture, airplanes, bikes, etc. We present a framework that enables a user to interactively design a probability density function (pdf) over such a shape space and to sample models according to the designed pdf. First, we propose a user interface that enables a user to quickly provide preference scores for selected shapes and suggest sampling strategies to decide which models to present to the user to evaluate. Second, we propose a novel kernel function to encode the similarity between two procedural models. Third, we propose a framework to interpolate user preference scores by combining multiple techniques: function factorization, Gaussian process regression, autorelevance detection, and l1 regularization. Fourth, we modify the original grammars to generate models with a pdf proportional to the user preference scores. Finally, we provide evaluations of our user interface and framework parameters and a comparison to other exploratory modeling techniques using modeling tasks in five example shape spaces: furniture, low-rise buildings, skyscrapers, airplanes, and vegetation.
Nonparametric Regression with Common Shocks
Directory of Open Access Journals (Sweden)
Eduardo A. Souza-Rodrigues
2016-09-01
Full Text Available This paper considers a nonparametric regression model for cross-sectional data in the presence of common shocks. Common shocks are allowed to be very general in nature; they do not need to be finite dimensional with a known (small number of factors. I investigate the properties of the Nadaraya-Watson kernel estimator and determine how general the common shocks can be while still obtaining meaningful kernel estimates. Restrictions on the common shocks are necessary because kernel estimators typically manipulate conditional densities, and conditional densities do not necessarily exist in the present case. By appealing to disintegration theory, I provide sufficient conditions for the existence of such conditional densities and show that the estimator converges in probability to the Kolmogorov conditional expectation given the sigma-field generated by the common shocks. I also establish the rate of convergence and the asymptotic distribution of the kernel estimator.
Bayesian nonparametric data analysis
Müller, Peter; Jara, Alejandro; Hanson, Tim
2015-01-01
This book reviews nonparametric Bayesian methods and models that have proven useful in the context of data analysis. Rather than providing an encyclopedic review of probability models, the book’s structure follows a data analysis perspective. As such, the chapters are organized by traditional data analysis problems. In selecting specific nonparametric models, simpler and more traditional models are favored over specialized ones. The discussed methods are illustrated with a wealth of examples, including applications ranging from stylized examples to case studies from recent literature. The book also includes an extensive discussion of computational methods and details on their implementation. R code for many examples is included in on-line software pages.
Failure Analysis of Wind Turbines by Probability Density Evolution Method
DEFF Research Database (Denmark)
Sichani, Mahdi Teimouri; Nielsen, Søren R.K.; Liu, W.F.
2013-01-01
The aim of this study is to present an efficient and accurate method for estimation of the failure probability of wind turbine structures which work under turbulent wind load. The classical method for this is to fit one of the extreme value probability distribution functions to the extracted maxima...
Lei, Youming; Zheng, Fan
2016-12-01
Stochastic chaos induced by diffusion processes, with identical spectral density but different probability density functions (PDFs), is investigated in selected lightly damped Hamiltonian systems. The threshold amplitude of diffusion processes for the onset of chaos is derived by using the stochastic Melnikov method together with a mean-square criterion. Two quasi-Hamiltonian systems, namely, a damped single pendulum and damped Duffing oscillator perturbed by stochastic excitations, are used as illustrative examples. Four different cases of stochastic processes are taking as the driving excitations. It is shown that in such two systems the spectral density of diffusion processes completely determines the threshold amplitude for chaos, regardless of the shape of their PDFs, Gaussian or otherwise. Furthermore, the mean top Lyapunov exponent is employed to verify analytical results. The results obtained by numerical simulations are in accordance with the analytical results. This demonstrates that the stochastic Melnikov method is effective in predicting the onset of chaos in the quasi-Hamiltonian systems.
Lei, Youming; Zheng, Fan
2016-12-01
Stochastic chaos induced by diffusion processes, with identical spectral density but different probability density functions (PDFs), is investigated in selected lightly damped Hamiltonian systems. The threshold amplitude of diffusion processes for the onset of chaos is derived by using the stochastic Melnikov method together with a mean-square criterion. Two quasi-Hamiltonian systems, namely, a damped single pendulum and damped Duffing oscillator perturbed by stochastic excitations, are used as illustrative examples. Four different cases of stochastic processes are taking as the driving excitations. It is shown that in such two systems the spectral density of diffusion processes completely determines the threshold amplitude for chaos, regardless of the shape of their PDFs, Gaussian or otherwise. Furthermore, the mean top Lyapunov exponent is employed to verify analytical results. The results obtained by numerical simulations are in accordance with the analytical results. This demonstrates that the stochastic Melnikov method is effective in predicting the onset of chaos in the quasi-Hamiltonian systems.
Assumed Probability Density Functions for Shallow and Deep Convection
Directory of Open Access Journals (Sweden)
Steven K Krueger
2010-10-01
Full Text Available The assumed joint probability density function (PDF between vertical velocity and conserved temperature and total water scalars has been suggested to be a relatively computationally inexpensive and unified subgrid-scale (SGS parameterization for boundary layer clouds and turbulent moments. This paper analyzes the performance of five families of PDFs using large-eddy simulations of deep convection, shallow convection, and a transition from stratocumulus to trade wind cumulus. Three of the PDF families are based on the double Gaussian form and the remaining two are the single Gaussian and a Double Delta Function (analogous to a mass flux model. The assumed PDF method is tested for grid sizes as small as 0.4 km to as large as 204.8 km. In addition, studies are performed for PDF sensitivity to errors in the input moments and for how well the PDFs diagnose some higher-order moments. In general, the double Gaussian PDFs more accurately represent SGS cloud structure and turbulence moments in the boundary layer compared to the single Gaussian and Double Delta Function PDFs for the range of grid sizes tested. This is especially true for small SGS cloud fractions. While the most complex PDF, Lewellen-Yoh, better represents shallow convective cloud properties (cloud fraction and liquid water mixing ratio compared to the less complex Analytic Double Gaussian 1 PDF, there appears to be no advantage in implementing Lewellen-Yoh for deep convection. However, the Analytic Double Gaussian 1 PDF better represents the liquid water flux, is less sensitive to errors in the input moments, and diagnoses higher order moments more accurately. Between the Lewellen-Yoh and Analytic Double Gaussian 1 PDFs, it appears that neither family is distinctly better at representing cloudy layers. However, due to the reduced computational cost and fairly robust results, it appears that the Analytic Double Gaussian 1 PDF could be an ideal family for SGS cloud and turbulence
Non-Parametric Inference in Astrophysics
Wasserman, L H; Nichol, R C; Genovese, C; Jang, W; Connolly, A J; Moore, A W; Schneider, J; Wasserman, Larry; Miller, Christopher J.; Nichol, Robert C.; Genovese, Chris; Jang, Woncheol; Connolly, Andrew J.; Moore, Andrew W.; Schneider, Jeff; group, the PICA
2001-01-01
We discuss non-parametric density estimation and regression for astrophysics problems. In particular, we show how to compute non-parametric confidence intervals for the location and size of peaks of a function. We illustrate these ideas with recent data on the Cosmic Microwave Background. We also briefly discuss non-parametric Bayesian inference.
Particle number and probability density functional theory and A-representability.
Pan, Xiao-Yin; Sahni, Viraht
2010-04-28
In Hohenberg-Kohn density functional theory, the energy E is expressed as a unique functional of the ground state density rho(r): E = E[rho] with the internal energy component F(HK)[rho] being universal. Knowledge of the functional F(HK)[rho] by itself, however, is insufficient to obtain the energy: the particle number N is primary. By emphasizing this primacy, the energy E is written as a nonuniversal functional of N and probability density p(r): E = E[N,p]. The set of functions p(r) satisfies the constraints of normalization to unity and non-negativity, exists for each N; N = 1, ..., infinity, and defines the probability density or p-space. A particle number N and probability density p(r) functional theory is constructed. Two examples for which the exact energy functionals E[N,p] are known are provided. The concept of A-representability is introduced, by which it is meant the set of functions Psi(p) that leads to probability densities p(r) obtained as the quantum-mechanical expectation of the probability density operator, and which satisfies the above constraints. We show that the set of functions p(r) of p-space is equivalent to the A-representable probability density set. We also show via the Harriman and Gilbert constructions that the A-representable and N-representable probability density p(r) sets are equivalent.
Antonelli, Cristian; Mecozzi, Antonio
2004-05-15
We give an analytical expression for the probability density function of the differential group delay for a concatenation of Maxwellian fiber sections and an arbitrary number of lumped elements with constant and isotropically oriented birefringence. When the contribution of the average squared of the constant birefringence elements is a significant fraction of the total, we show that the outage probability can be significantly overestimated if the probability density function of the differential group delay is approximated by a Maxwellian distribution.
Examples of the Application of Nonparametric Information Geometry to Statistical Physics
Directory of Open Access Journals (Sweden)
Giovanni Pistone
2013-09-01
Full Text Available We review a nonparametric version of Amari’s information geometry in which the set of positive probability densities on a given sample space is endowed with an atlas of charts to form a differentiable manifold modeled on Orlicz Banach spaces. This nonparametric setting is used to discuss the setting of typical problems in machine learning and statistical physics, such as black-box optimization, Kullback-Leibler divergence, Boltzmann-Gibbs entropy and the Boltzmann equation.
Local Component Analysis for Nonparametric Bayes Classifier
Khademi, Mahmoud; safayani, Meharn
2010-01-01
The decision boundaries of Bayes classifier are optimal because they lead to maximum probability of correct decision. It means if we knew the prior probabilities and the class-conditional densities, we could design a classifier which gives the lowest probability of error. However, in classification based on nonparametric density estimation methods such as Parzen windows, the decision regions depend on the choice of parameters such as window width. Moreover, these methods suffer from curse of dimensionality of the feature space and small sample size problem which severely restricts their practical applications. In this paper, we address these problems by introducing a novel dimension reduction and classification method based on local component analysis. In this method, by adopting an iterative cross-validation algorithm, we simultaneously estimate the optimal transformation matrices (for dimension reduction) and classifier parameters based on local information. The proposed method can classify the data with co...
DEFF Research Database (Denmark)
Sichani, Mahdi Teimouri; Nielsen, Søren R.K.; Liu, W. F.
2013-01-01
Estimation of extreme response and failure probability of structures subjected to ultimate design loads is essential for structural design of wind turbines according to the new standard IEC61400-1. This task is focused on in the present paper in virtue of probability density evolution method (PDEM......), which underlies the schemes of random vibration analysis and structural reliability assessment. The short-term rare failure probability of 5-mega-watt wind turbines, for illustrative purposes, in case of given mean wind speeds and turbulence levels is investigated through the scheme of extreme value...... distribution instead of any other approximate schemes of fitted distribution currently used in statistical extrapolation techniques. Besides, the comparative studies against the classical fitted distributions and the standard Monte Carlo techniques are carried out. Numerical results indicate that PDEM exhibits...
On the discretization of probability density functions and the continuous Rényi entropy
Indian Academy of Sciences (India)
Diógenes Campos
2015-12-01
On the basis of second mean-value theorem (SMVT) for integrals, a discretization method is proposed with the aim of representing the expectation value of a function with respect to a probability density function in terms of the discrete probability theory. This approach is applied to the continuous Rényi entropy, and it is established that a discrete probability distribution can be associated to it in a very natural way. The probability density functions for the linear superposition of two coherent states is used for developing a representative example.
Recent Developments in Applied Probability and Statistics
Devroye, Luc; Kohler, Michael; Korn, Ralf
2010-01-01
This book presents surveys on recent developments in applied probability and statistics. The contributions include topics such as nonparametric regression and density estimation, option pricing, probabilistic methods for multivariate interpolation, robust graphical modelling and stochastic differential equations. Due to its broad coverage of different topics the book offers an excellent overview of recent developments in applied probability and statistics.
Institute of Scientific and Technical Information of China (English)
无
2009-01-01
【说词】1. He can probably tell us the truth.2. Will it rain this afternoong ？ Probably【解语】作副词，意为“大概、或许”，表示可能性很大，通常指根据目前情况作出积极推测或判断；
Minimax Robustness of Bayesian Forecasting under Functional Distortions of Probability Densities
Kharin, Alexey
2002-01-01
The problems of robustness in Bayesian forecasting are considered under distortions of the hypothetical probability densities. The expressions for the guaranteed upper risk functional are obtained and the robust prediction statistics under certain types of distortions are constructed.
Heisler, Lori; Goffman, Lisa
2016-01-01
A word learning paradigm was used to teach children novel words that varied in phonotactic probability and neighborhood density. The effects of frequency and density on speech production were examined when phonetic forms were nonreferential (i.e., when no referent was attached) and when phonetic forms were referential (i.e., when a referent was…
Heisler, Lori; Goffman, Lisa
2016-01-01
A word learning paradigm was used to teach children novel words that varied in phonotactic probability and neighborhood density. The effects of frequency and density on speech production were examined when phonetic forms were nonreferential (i.e., when no referent was attached) and when phonetic forms were referential (i.e., when a referent was…
Institute of Scientific and Technical Information of China (English)
无
2010-01-01
To analyze the effect of basic variable on failure probability in reliability analysis,a moment-independent importance measure of the basic random variable is proposed,and its properties are analyzed and verified.Based on this work,the importance measure of the basic variable on the failure probability is compared with that on the distribution density of the response.By use of the probability density evolution method,a solution is established to solve two importance measures,which can efficiently avoid the difficulty in solving the importance measures.Some numerical examples and engineering examples are used to demonstrate the proposed importance measure on the failure probability and that on the distribution density of the response.The results show that the proposed importance measure can effectively describe the effect of the basic variable on the failure probability from the distribution density of the basic variable.Additionally,the results show that the established solution on the probability density evolution is efficient for the importance measures.
The force distribution probability function for simple fluids by density functional theory.
Rickayzen, G; Heyes, D M
2013-02-28
Classical density functional theory (DFT) is used to derive a formula for the probability density distribution function, P(F), and probability distribution function, W(F), for simple fluids, where F is the net force on a particle. The final formula for P(F) ∝ exp(-AF(2)), where A depends on the fluid density, the temperature, and the Fourier transform of the pair potential. The form of the DFT theory used is only applicable to bounded potential fluids. When combined with the hypernetted chain closure of the Ornstein-Zernike equation, the DFT theory for W(F) agrees with molecular dynamics computer simulations for the Gaussian and bounded soft sphere at high density. The Gaussian form for P(F) is still accurate at lower densities (but not too low density) for the two potentials, but with a smaller value for the constant, A, than that predicted by the DFT theory.
Non-parametric estimation of Fisher information from real data
Shemesh, Omri Har; Miñano, Borja; Hoekstra, Alfons G; Sloot, Peter M A
2015-01-01
The Fisher Information matrix is a widely used measure for applications ranging from statistical inference, information geometry, experiment design, to the study of criticality in biological systems. Yet there is no commonly accepted non-parametric algorithm to estimate it from real data. In this rapid communication we show how to accurately estimate the Fisher information in a nonparametric way. We also develop a numerical procedure to minimize the errors by choosing the interval of the finite difference scheme necessary to compute the derivatives in the definition of the Fisher information. Our method uses the recently published "Density Estimation using Field Theory" algorithm to compute the probability density functions for continuous densities. We use the Fisher information of the normal distribution to validate our method and as an example we compute the temperature component of the Fisher Information Matrix in the two dimensional Ising model and show that it obeys the expected relation to the heat capa...
Institute of Scientific and Technical Information of China (English)
Pousga Kabore; Husam Baki; Hong Yue; Hong Wang
2005-01-01
This paper presents a linearized approach for the controller design of the shape of output probability density functions for general stochastic systems. A square root approximation to an output probability density function is realized by a set of B-spline functions. This generally produces a nonlinear state space model for the weights of the B-spline approximation. A linearized model is therefore obtained and embedded into a performance function that measures the tracking error of the output probability density function with respect to a given distribution. By using this performance function as a Lyapunov function for the closed loop system, a feedback control input has been obtained which guarantees closed loop stability and realizes perfect tracking. The algorithm described in this paper has been tested on a simulated example and desired results have been achieved.
Modelling the Probability Density Function of IPTV Traffic Packet Delay Variation
Directory of Open Access Journals (Sweden)
Michal Halas
2012-01-01
Full Text Available This article deals with modelling the Probability density function of IPTV traffic packet delay variation. The use of this modelling is in an efficient de-jitter buffer estimation. When an IP packet travels across a network, it experiences delay and its variation. This variation is caused by routing, queueing systems and other influences like the processing delay of the network nodes. When we try to separate these at least three types of delay variation, we need a way to measure these types separately. This work is aimed to the delay variation caused by queueing systems which has the main implications to the form of the Probability density function.
Nonparametric TOA estimators for low-resolution IR-UWB digital receiver
Institute of Scientific and Technical Information of China (English)
Yanlong Zhang; Weidong Chen
2015-01-01
Nonparametric time-of-arrival (TOA) estimators for im-pulse radio ultra-wideband (IR-UWB) signals are proposed. Non-parametric detection is obviously useful in situations where de-tailed information about the statistics of the noise is unavailable or not accurate. Such TOA estimators are obtained based on condi-tional statistical tests with only a symmetry distribution assumption on the noise probability density function. The nonparametric es-timators are attractive choices for low-resolution IR-UWB digital receivers which can be implemented by fast comparators or high sampling rate low resolution analog-to-digital converters (ADCs), in place of high sampling rate high resolution ADCs which may not be available in practice. Simulation results demonstrate that nonparametric TOA estimators provide more effective and robust performance than typical energy detection (ED) based estimators.
Heisler, Lori; Goffman, Lisa
A word learning paradigm was used to teach children novel words that varied in phonotactic probability and neighborhood density. The effects of frequency and density on speech production were examined when phonetic forms were non-referential (i.e., when no referent was attached) and when phonetic forms were referential (i.e., when a referent was attached through fast mapping). Two methods of analysis were included: (1) kinematic variability of speech movement patterning; and (2) measures of segmental accuracy. Results showed that phonotactic frequency influenced the stability of movement patterning whereas neighborhood density influenced phoneme accuracy. Motor learning was observed in both non-referential and referential novel words. Forms with low phonotactic probability and low neighborhood density showed a word learning effect when a referent was assigned during fast mapping. These results elaborate on and specify the nature of interactivity observed across lexical, phonological, and articulatory domains.
Energy Technology Data Exchange (ETDEWEB)
Carr, D.B.; Tolley, H.D.
1982-12-01
This paper investigates procedures for univariate nonparametric estimation of tail probabilities. Extrapolated values for tail probabilities beyond the data are also obtained based on the shape of the density in the tail. Several estimators which use exponential weighting are described. These are compared in a Monte Carlo study to nonweighted estimators, to the empirical cdf, to an integrated kernel, to a Fourier series estimate, to a penalized likelihood estimate and a maximum likelihood estimate. Selected weighted estimators are shown to compare favorably to many of these standard estimators for the sampling distributions investigated.
Effect on Prediction when Modeling Covariates in Bayesian Nonparametric Models.
Cruz-Marcelo, Alejandro; Rosner, Gary L; Müller, Peter; Stewart, Clinton F
2013-04-01
In biomedical research, it is often of interest to characterize biologic processes giving rise to observations and to make predictions of future observations. Bayesian nonparametric methods provide a means for carrying out Bayesian inference making as few assumptions about restrictive parametric models as possible. There are several proposals in the literature for extending Bayesian nonparametric models to include dependence on covariates. Limited attention, however, has been directed to the following two aspects. In this article, we examine the effect on fitting and predictive performance of incorporating covariates in a class of Bayesian nonparametric models by one of two primary ways: either in the weights or in the locations of a discrete random probability measure. We show that different strategies for incorporating continuous covariates in Bayesian nonparametric models can result in big differences when used for prediction, even though they lead to otherwise similar posterior inferences. When one needs the predictive density, as in optimal design, and this density is a mixture, it is better to make the weights depend on the covariates. We demonstrate these points via a simulated data example and in an application in which one wants to determine the optimal dose of an anticancer drug used in pediatric oncology.
Semi- and Nonparametric ARCH Processes
Directory of Open Access Journals (Sweden)
Oliver B. Linton
2011-01-01
Full Text Available ARCH/GARCH modelling has been successfully applied in empirical finance for many years. This paper surveys the semiparametric and nonparametric methods in univariate and multivariate ARCH/GARCH models. First, we introduce some specific semiparametric models and investigate the semiparametric and nonparametrics estimation techniques applied to: the error density, the functional form of the volatility function, the relationship between mean and variance, long memory processes, locally stationary processes, continuous time processes and multivariate models. The second part of the paper is about the general properties of such processes, including stationary conditions, ergodic conditions and mixing conditions. The last part is on the estimation methods in ARCH/GARCH processes.
Dynamic Graphics in Excel for Teaching Statistics: Understanding the Probability Density Function
Coll-Serrano, Vicente; Blasco-Blasco, Olga; Alvarez-Jareno, Jose A.
2011-01-01
In this article, we show a dynamic graphic in Excel that is used to introduce an important concept in our subject, Statistics I: the probability density function. This interactive graphic seeks to facilitate conceptual understanding of the main aspects analysed by the learners.
Influence of Phonotactic Probability/Neighbourhood Density on Lexical Learning in Late Talkers
MacRoy-Higgins, Michelle; Schwartz, Richard G.; Shafer, Valerie L.; Marton, Klara
2013-01-01
Background: Toddlers who are late talkers demonstrate delays in phonological and lexical skills. However, the influence of phonological factors on lexical acquisition in toddlers who are late talkers has not been examined directly. Aims: To examine the influence of phonotactic probability/neighbourhood density on word learning in toddlers who were…
Maslennikova, Yu. S.; Nugmanov, I. S.
2016-08-01
The problem of probability density function estimation for a random process is one of the most common in practice. There are several methods to solve this problem. Presented laboratory work uses methods of the mathematical statistics to detect patterns in the realization of random process. On the basis of ergodic theory, we construct algorithm for estimating univariate probability density distribution function for a random process. Correlational analysis of realizations is applied to estimate the necessary size of the sample and the time of observation. Hypothesis testing for two probability distributions (normal and Cauchy) is used on the experimental data, using χ2 criterion. To facilitate understanding and clarity of the problem solved, we use ELVIS II platform and LabVIEW software package that allows us to make the necessary calculations, display results of the experiment and, most importantly, to control the experiment. At the same time students are introduced to a LabVIEW software package and its capabilities.
Energy Technology Data Exchange (ETDEWEB)
Wampler, William R.; Myers, Samuel M.; Modine, Normand A.
2017-09-01
The energy-dependent probability density of tunneled carrier states for arbitrarily specified longitudinal potential-energy profiles in planar bipolar devices is numerically computed using the scattering method. Results agree accurately with a previous treatment based on solution of the localized eigenvalue problem, where computation times are much greater. These developments enable quantitative treatment of tunneling-assisted recombination in irradiated heterojunction bipolar transistors, where band offsets may enhance the tunneling effect by orders of magnitude. The calculations also reveal the density of non-tunneled carrier states in spatially varying potentials, and thereby test the common approximation of uniform- bulk values for such densities.
Analysis of 2-d ultrasound cardiac strain imaging using joint probability density functions.
Ma, Chi; Varghese, Tomy
2014-06-01
Ultrasound frame rates play a key role for accurate cardiac deformation tracking. Insufficient frame rates lead to an increase in signal de-correlation artifacts resulting in erroneous displacement and strain estimation. Joint probability density distributions generated from estimated axial strain and its associated signal-to-noise ratio provide a useful approach to assess the minimum frame rate requirements. Previous reports have demonstrated that bi-modal distributions in the joint probability density indicate inaccurate strain estimation over a cardiac cycle. In this study, we utilize similar analysis to evaluate a 2-D multi-level displacement tracking and strain estimation algorithm for cardiac strain imaging. The effect of different frame rates, final kernel dimensions and a comparison of radio frequency and envelope based processing are evaluated using echo signals derived from a 3-D finite element cardiac model and five healthy volunteers. Cardiac simulation model analysis demonstrates that the minimum frame rates required to obtain accurate joint probability distributions for the signal-to-noise ratio and strain, for a final kernel dimension of 1 λ by 3 A-lines, was around 42 Hz for radio frequency signals. On the other hand, even a frame rate of 250 Hz with envelope signals did not replicate the ideal joint probability distribution. For the volunteer study, clinical data was acquired only at a 34 Hz frame rate, which appears to be sufficient for radio frequency analysis. We also show that an increase in the final kernel dimensions significantly affect the strain probability distribution and joint probability density function generated, with a smaller effect on the variation in the accumulated mean strain estimated over a cardiac cycle. Our results demonstrate that radio frequency frame rates currently achievable on clinical cardiac ultrasound systems are sufficient for accurate analysis of the strain probability distribution, when a multi-level 2-D
Evolving Molecular Cloud Structure and the Column Density Probability Distribution Function
Ward, Rachel L; Sills, Alison
2014-01-01
The structure of molecular clouds can be characterized with the probability distribution function (PDF) of the mass surface density. In particular, the properties of the distribution can reveal the nature of the turbulence and star formation present inside the molecular cloud. In this paper, we explore how these structural characteristics evolve with time and also how they relate to various cloud properties as measured from a sample of synthetic column density maps of molecular clouds. We find that, as a cloud evolves, the peak of its column density PDF will shift to surface densities below the observational threshold for detection, resulting in an underlying lognormal distribution which has been effectively lost at late times. Our results explain why certain observations of actively star-forming, dynamically older clouds, such as the Orion molecular cloud, do not appear to have any evidence of a lognormal distribution in their column density PDFs. We also study the evolution of the slope and deviation point ...
Nonparametric estimation of Fisher information from real data
Har-Shemesh, Omri; Quax, Rick; Miñano, Borja; Hoekstra, Alfons G.; Sloot, Peter M. A.
2016-02-01
The Fisher information matrix (FIM) is a widely used measure for applications including statistical inference, information geometry, experiment design, and the study of criticality in biological systems. The FIM is defined for a parametric family of probability distributions and its estimation from data follows one of two paths: either the distribution is assumed to be known and the parameters are estimated from the data or the parameters are known and the distribution is estimated from the data. We consider the latter case which is applicable, for example, to experiments where the parameters are controlled by the experimenter and a complicated relation exists between the input parameters and the resulting distribution of the data. Since we assume that the distribution is unknown, we use a nonparametric density estimation on the data and then compute the FIM directly from that estimate using a finite-difference approximation to estimate the derivatives in its definition. The accuracy of the estimate depends on both the method of nonparametric estimation and the difference Δ θ between the densities used in the finite-difference formula. We develop an approach for choosing the optimal parameter difference Δ θ based on large deviations theory and compare two nonparametric density estimation methods, the Gaussian kernel density estimator and a novel density estimation using field theory method. We also compare these two methods to a recently published approach that circumvents the need for density estimation by estimating a nonparametric f divergence and using it to approximate the FIM. We use the Fisher information of the normal distribution to validate our method and as a more involved example we compute the temperature component of the FIM in the two-dimensional Ising model and show that it obeys the expected relation to the heat capacity and therefore peaks at the phase transition at the correct critical temperature.
Institute of Scientific and Technical Information of China (English)
张路平; 王鲁平; 李飚; 赵明
2015-01-01
In order to improve the performance of the probability hypothesis density (PHD) algorithm based particle filter (PF) in terms of number estimation and states extraction of multiple targets, a new probability hypothesis density filter algorithm based on marginalized particle and kernel density estimation is proposed, which utilizes the idea of marginalized particle filter to enhance the estimating performance of the PHD. The state variables are decomposed into linear and non-linear parts. The particle filter is adopted to predict and estimate the nonlinear states of multi-target after dimensionality reduction, while the Kalman filter is applied to estimate the linear parts under linear Gaussian condition. Embedding the information of the linear states into the estimated nonlinear states helps to reduce the estimating variance and improve the accuracy of target number estimation. The meanshift kernel density estimation, being of the inherent nature of searching peak value via an adaptive gradient ascent iteration, is introduced to cluster particles and extract target states, which is independent of the target number and can converge to the local peak position of the PHD distribution while avoiding the errors due to the inaccuracy in modeling and parameters estimation. Experiments show that the proposed algorithm can obtain higher tracking accuracy when using fewer sampling particles and is of lower computational complexity compared with the PF-PHD.
Protein distance constraints predicted by neural networks and probability density functions
DEFF Research Database (Denmark)
Lund, Ole; Frimand, Kenneth; Gorodkin, Jan
1997-01-01
We predict interatomic C-α distances by two independent data driven methods. The first method uses statistically derived probability distributions of the pairwise distance between two amino acids, whilst the latter method consists of a neural network prediction approach equipped with windows taking....... The predictions are based on a data set derived using a new threshold similarity. We show that distances in proteins are predicted more accurately by neural networks than by probability density functions. We show that the accuracy of the predictions can be further increased by using sequence profiles. A threading...
Ensemble Averaged Probability Density Function (APDF) for Compressible Turbulent Reacting Flows
Shih, Tsan-Hsing; Liu, Nan-Suey
2012-01-01
In this paper, we present a concept of the averaged probability density function (APDF) for studying compressible turbulent reacting flows. The APDF is defined as an ensemble average of the fine grained probability density function (FG-PDF) with a mass density weighting. It can be used to exactly deduce the mass density weighted, ensemble averaged turbulent mean variables. The transport equation for APDF can be derived in two ways. One is the traditional way that starts from the transport equation of FG-PDF, in which the compressible Navier- Stokes equations are embedded. The resulting transport equation of APDF is then in a traditional form that contains conditional means of all terms from the right hand side of the Navier-Stokes equations except for the chemical reaction term. These conditional means are new unknown quantities that need to be modeled. Another way of deriving the transport equation of APDF is to start directly from the ensemble averaged Navier-Stokes equations. The resulting transport equation of APDF derived from this approach appears in a closed form without any need for additional modeling. The methodology of ensemble averaging presented in this paper can be extended to other averaging procedures: for example, the Reynolds time averaging for statistically steady flow and the Reynolds spatial averaging for statistically homogeneous flow. It can also be extended to a time or spatial filtering procedure to construct the filtered density function (FDF) for the large eddy simulation (LES) of compressible turbulent reacting flows.
DEFF Research Database (Denmark)
Nielsen, Søren R. K.; Peng, Yongbo; Sichani, Mahdi Teimouri
2016-01-01
The paper deals with the response and reliability analysis of hysteretic or geometric nonlinear uncertain dynamical systems of arbitrary dimensionality driven by stochastic processes. The approach is based on the probability density evolution method proposed by Li and Chen (Stochastic dynamics...... of structures, 1st edn. Wiley, London, 2009; Probab Eng Mech 20(1):33–44, 2005), which circumvents the dimensional curse of traditional methods for the determination of non-stationary probability densities based on Markov process assumptions and the numerical solution of the related Fokker–Planck and Kolmogorov......–Feller equations. The main obstacle of the method is that a multi-dimensional convolution integral needs to be carried out over the sample space of a set of basic random variables, for which reason the number of these need to be relatively low. In order to handle this problem an approach is suggested, which...
Kauffmann, Steven Kenneth
2013-01-01
The quantum mechanics status of the probability vector current density has long seemed to be marginal. On one hand no systematic prescription for its construction is provided, and the special examples of it that are obtained for particular types of Hamiltonian operator could conceivably be attributed to happenstance. On the other hand this concept's key physical interpretation as local average particle flux, which flows from the equation of continuity that it is supposed to satisfy in conjunction with the probability scalar density, has been claimed to breach the uncertainty principle. Given the dispiriting impact of that claim, we straightaway point out that the subtle directional nature of the uncertainty principle makes it consistent with the measurement of local average particle flux. We next focus on the fact that the unique closed-form linear-superposition quantization of any classical Hamiltonian function yields in tandem the corresponding unique linear-superposition closed-form divergence of the proba...
Probability-hypothesis-density filter for multitarget visual tracking with trajectory recognition
Wu, Jingjing; Hu, Shiqiang; Wang, Yang
2010-12-01
The probability-hypothesis-density (PHD) filter as a multitarget recursive Bayes filter has generated substantial interest in the visual tracking field due to its ability to handle a time-varying number of targets. But the target's trajectory cannot be identified within its own framework. To complement the ability of PHD, the auction algorithm is combined to calculate the object trajectories automatically. We present a motion detection, dynamic, and measurement equation, as well as visual multitarget tracking algorithm based on Gaussian mixture probability hypothesis density with trajectory computation in detail. Experimental results on a large video surveillance dataset show that the proposed multitarget tracking framework improves the tracker and recognizes tracks when a variable number of targets appear, merge, split, and disappear, even in cluttered scenes.
Probability Density Function for Waves Propagating in a Straight PEC Rough Wall Tunnel
Energy Technology Data Exchange (ETDEWEB)
Pao, H
2004-11-08
The probability density function for wave propagating in a straight perfect electrical conductor (PEC) rough wall tunnel is deduced from the mathematical models of the random electromagnetic fields. The field propagating in caves or tunnels is a complex-valued Gaussian random processing by the Central Limit Theorem. The probability density function for single modal field amplitude in such structure is Ricean. Since both expected value and standard deviation of this field depend only on radial position, the probability density function, which gives what is the power distribution, is a radially dependent function. The radio channel places fundamental limitations on the performance of wireless communication systems in tunnels and caves. The transmission path between the transmitter and receiver can vary from a simple direct line of sight to one that is severely obstructed by rough walls and corners. Unlike wired channels that are stationary and predictable, radio channels can be extremely random and difficult to analyze. In fact, modeling the radio channel has historically been one of the more challenging parts of any radio system design; this is often done using statistical methods. In this contribution, we present the most important statistic property, the field probability density function, of wave propagating in a straight PEC rough wall tunnel. This work only studies the simplest case--PEC boundary which is not the real world but the methods and conclusions developed herein are applicable to real world problems which the boundary is dielectric. The mechanisms behind electromagnetic wave propagation in caves or tunnels are diverse, but can generally be attributed to reflection, diffraction, and scattering. Because of the multiple reflections from rough walls, the electromagnetic waves travel along different paths of varying lengths. The interactions between these waves cause multipath fading at any location, and the strengths of the waves decrease as the distance
Energy Quantization and Probability Density of Electron in Intense-Field-Atom Interactions
Institute of Scientific and Technical Information of China (English)
敖淑艳; 程太旺; 李晓峰; 吴令安; 付盘铭
2003-01-01
We find that, due to the quantum correlation between the electron and the field, the electronic energy becomes quantized also, manifesting the particle aspect of light in the electron-light interaction. The probability amplitude of finding electron with a given energy is given by a generalized Bessel function, which can be represented as a coherent superposition of contributions from a few electronic quantum trajectories. This concept is illustrated by comparing the spectral density of the electron with the laser assisted recombination spectrum.
Steady-state probability density function in wave turbulence under large volume limit
Institute of Scientific and Technical Information of China (English)
Yeontaek Choia; Sang Gyu Job
2011-01-01
We investigate the possibility for two-mode probability density function (PDF) to have a non-zero flux steady state solution. We take the large volume limit so that the space of modes becomes continuous. It is shown that in this limit all the steady-state two- or higher-mode PDFs are the product of one-mode PDFs. The flux of this steady-state solution turns out to be zero for any finite mode PDF.
Analytical formulation of the single-visit completeness joint probability density function
Garrett, Daniel
2016-01-01
We derive an exact formulation of the multivariate integral representing the single-visit obscurational and photometric completeness joint probability density function for arbitrary distributions for planetary parameters. We present a derivation of the region of nonzero values of this function which extends previous work, and discuss time and computational complexity costs and benefits of the method. We present a working implementation, and demonstrate excellent agreement between this approach and Monte Carlo simulation results
DEFF Research Database (Denmark)
Falk, Anne Katrine Vinther; Gryning, Sven-Erik
1997-01-01
In this model for atmospheric dispersion particles are simulated by the Langevin Equation, which is a stochastic differential equation. It uses the probability density function (PDF) of the vertical velocity fluctuations as input. The PDF is constructed as an expansion after Hermite polynomials....... In several previous works where the PDF was expressed this way, further use was hampered by the fact that the PDF takes negative values for a range of velocities. This problem is overcome in the present formulation...
Directory of Open Access Journals (Sweden)
Peng Gao
2014-01-01
Full Text Available It is necessary to develop dynamic reliability models when considering strength degradation of mechanical components. Instant probability density function (IPDF of stress and process probability density function (PPDF of stress, which are obtained via different statistical methods, are defined, respectively. In practical engineering, the probability density function (PDF for the usage of mechanical components is mostly PPDF, such as the PDF acquired via the rain flow counting method. For the convenience of application, IPDF is always approximated by PPDF when using the existing dynamic reliability models. However, it may cause errors in the reliability calculation due to the approximation of IPDF by PPDF. Therefore, dynamic reliability models directly based on PPDF of stress are developed in this paper. Furthermore, the proposed models can be used for reliability assessment in the case of small amount of stress process samples by employing the fuzzy set theory. In addition, the mechanical components in solar array of satellites are chosen as representative examples to illustrate the proposed models. The results show that errors are caused because of the approximation of IPDF by PPDF and the proposed models are accurate in the reliability computation.
Unification of field theory and maximum entropy methods for learning probability densities.
Kinney, Justin B
2015-09-01
The need to estimate smooth probability distributions (a.k.a. probability densities) from finite sampled data is ubiquitous in science. Many approaches to this problem have been described, but none is yet regarded as providing a definitive solution. Maximum entropy estimation and Bayesian field theory are two such approaches. Both have origins in statistical physics, but the relationship between them has remained unclear. Here I unify these two methods by showing that every maximum entropy density estimate can be recovered in the infinite smoothness limit of an appropriate Bayesian field theory. I also show that Bayesian field theory estimation can be performed without imposing any boundary conditions on candidate densities, and that the infinite smoothness limit of these theories recovers the most common types of maximum entropy estimates. Bayesian field theory thus provides a natural test of the maximum entropy null hypothesis and, furthermore, returns an alternative (lower entropy) density estimate when the maximum entropy hypothesis is falsified. The computations necessary for this approach can be performed rapidly for one-dimensional data, and software for doing this is provided.
Nonparametric k-nearest-neighbor entropy estimator.
Lombardi, Damiano; Pant, Sanjay
2016-01-01
A nonparametric k-nearest-neighbor-based entropy estimator is proposed. It improves on the classical Kozachenko-Leonenko estimator by considering nonuniform probability densities in the region of k-nearest neighbors around each sample point. It aims to improve the classical estimators in three situations: first, when the dimensionality of the random variable is large; second, when near-functional relationships leading to high correlation between components of the random variable are present; and third, when the marginal variances of random variable components vary significantly with respect to each other. Heuristics on the error of the proposed and classical estimators are presented. Finally, the proposed estimator is tested for a variety of distributions in successively increasing dimensions and in the presence of a near-functional relationship. Its performance is compared with a classical estimator, and a significant improvement is demonstrated.
Ossenkopf, Volker; Schneider, Nicola; Federrath, Christoph; Klessen, Ralf S
2016-01-01
Probability distribution functions (PDFs) of column densities are an established tool to characterize the evolutionary state of interstellar clouds. Using simulations, we show to what degree their determination is affected by noise, line-of-sight contamination, field selection, and the incomplete sampling in interferometric measurements. We solve the integrals that describe the convolution of a cloud PDF with contaminating sources and study the impact of missing information on the measured column density PDF. The effect of observational noise can be easily estimated and corrected for if the root mean square (rms) of the noise is known. For $\\sigma_{noise}$ values below 40\\,\\% of the typical cloud column density, $N_{peak}$, this involves almost no degradation of the accuracy of the PDF parameters. For higher noise levels and narrow cloud PDFs the width of the PDF becomes increasingly uncertain. A contamination by turbulent foreground or background clouds can be removed as a constant shield if the PDF of the c...
Nonparametric statistical inference
Gibbons, Jean Dickinson
2010-01-01
Overall, this remains a very fine book suitable for a graduate-level course in nonparametric statistics. I recommend it for all people interested in learning the basic ideas of nonparametric statistical inference.-Eugenia Stoimenova, Journal of Applied Statistics, June 2012… one of the best books available for a graduate (or advanced undergraduate) text for a theory course on nonparametric statistics. … a very well-written and organized book on nonparametric statistics, especially useful and recommended for teachers and graduate students.-Biometrics, 67, September 2011This excellently presente
Rebola, João L.; Cartaxo, Adolfo V. T.
The influence of the concatenation of arbitrary optical multiplexers/demultiplexers (MUX/DEMUXs) on the probability density function (PDF) of the output current of a transparent optical network is assessed. All PDF results obtained analytically are compared with estimates from Monte Carlo simulation and an excellent agreement is achieved. The non-Gaussian behavior of the PDFs, previously reported by other authors for square-law detectors, is significantly enhanced with the number of nodes increase due to the noise accumulation along the cascade of MUX/DEMUXs. The increase of the MUX/DEMUXs bandwidth and detuning also enhances the PDFs non-Gaussian behavior. The PDF shape variation with the detuning depends strongly on the number of nodes. Explanations for the Gaussian approximation (GA) accuracy on the assessment of the performance of a concatenation of optical MUX/DEMUXs are also provided. For infinite extinction ratio and tuned MUX/DEMUXs, the GA error probabilities are, in general, pessimistic, due to the inaccurate estimation of the error probability for both bits. For low extinction ratio, the GA is very accurate due to a balance between the error probabilities estimated for the bits "1" and "0." With the detuning increase, the GA estimates can become optimistic.
Gulev, Sergey; Tilinina, Natalia; Belyaev, Konstantin
2015-04-01
Surface turbulent heat fluxes from modern era and first generation reanalyses (NCEP-DOE, ERA-Interim, MERRA NCEP-CFSR, JRA) as well as from satellite products (SEAFLUX, IFREMER, HOAPS) were intercompared using framework of probability distributions for sensible and latent heat fluxes. For approximation of probability distributions and estimation of extreme flux values Modified Fisher-Tippett (MFT) distribution has been used. Besides mean flux values, consideration is given to the comparative analysis of (i) parameters of the MFT probability density functions (scale and location), (ii) extreme flux values corresponding high order percentiles of fluxes (e.g. 99th and higher) and (iii) fractional contribution of extreme surface flux events in the total surface turbulent fluxes integrated over months and seasons. The latter was estimated using both fractional distribution derived from MFT and empirical estimates based upon occurrence histograms. The strongest differences in the parameters of probability distributions of surface fluxes and extreme surface flux values between different reanalyses are found in the western boundary current extension regions and high latitudes, while the highest differences in the fractional contributions of surface fluxes may occur in mid ocean regions being closely associated with atmospheric synoptic dynamics. Generally, satellite surface flux products demonstrate relatively stronger extreme fluxes compared to reanalyses, even in the Northern Hemisphere midlatitudes where data assimilation input in reanalyses is quite dense compared to the Southern Ocean regions.
Storkel, Holly L.; Bontempo, Daniel E.; Aschenbrenner, Andrew J.; Maekawa, Junko; Lee, Su-Yeon
2013-01-01
Purpose: Phonotactic probability or neighborhood density has predominately been defined through the use of gross distinctions (i.e., low vs. high). In the current studies, the authors examined the influence of finer changes in probability (Experiment 1) and density (Experiment 2) on word learning. Method: The authors examined the full range of…
Storkel, Holly L.; Bontempo, Daniel E.; Aschenbrenner, Andrew J.; Maekawa, Junko; Lee, Su-Yeon
2013-01-01
Purpose: Phonotactic probability or neighborhood density has predominately been defined through the use of gross distinctions (i.e., low vs. high). In the current studies, the authors examined the influence of finer changes in probability (Experiment 1) and density (Experiment 2) on word learning. Method: The authors examined the full range of…
Bakosi, J; Boybeyi, Z
2010-01-01
In probability density function (PDF) methods a transport equation is solved numerically to compute the time and space dependent probability distribution of several flow variables in a turbulent flow. The joint PDF of the velocity components contains information on all one-point one-time statistics of the turbulent velocity field, including the mean, the Reynolds stresses and higher-order statistics. We developed a series of numerical algorithms to model the joint PDF of turbulent velocity, frequency and scalar compositions for high-Reynolds-number incompressible flows in complex geometries using unstructured grids. Advection, viscous diffusion and chemical reaction appear in closed form in the PDF formulation, thus require no closure hypotheses. The generalized Langevin model (GLM) is combined with an elliptic relaxation technique to represent the non-local effect of walls on the pressure redistribution and anisotropic dissipation of turbulent kinetic energy. The governing system of equations is solved fully...
Carr, Thomas W
2017-02-01
In an SIRS compartment model for a disease we consider the effect of different probability distributions for remaining immune. We show that to first approximation the first three moments of the corresponding probability densities are sufficient to well describe oscillatory solutions corresponding to recurrent epidemics. Specifically, increasing the fraction who lose immunity, increasing the mean immunity time, and decreasing the heterogeneity of the population all favor the onset of epidemics and increase their severity. We consider six different distributions, some symmetric about their mean and some asymmetric, and show that by tuning their parameters such that they have equivalent moments that they all exhibit equivalent dynamical behavior. Copyright © 2016 Elsevier Inc. All rights reserved.
Spline Histogram Method for Reconstruction of Probability Density Functions of Clusters of Galaxies
Docenko, Dmitrijs; Berzins, Karlis
We describe the spline histogram algorithm which is useful for visualization of the probability density function setting up a statistical hypothesis for a test. The spline histogram is constructed from discrete data measurements using tensioned cubic spline interpolation of the cumulative distribution function which is then differentiated and smoothed using the Savitzky-Golay filter. The optimal width of the filter is determined by minimization of the Integrated Square Error function. The current distribution of the TCSplin algorithm written in f77 with IDL and Gnuplot visualization scripts is available from www.virac.lv/en/soft.html.
Spline histogram method for reconstruction of probability density function of clusters of galaxies
Docenko, D; Docenko, Dmitrijs; Berzins, Karlis
2003-01-01
We describe the spline histogram algorithm which is useful for visualization of the probability density function setting up a statistical hypothesis for a test. The spline histogram is constructed from discrete data measurements using tensioned cubic spline interpolation of the cumulative distribution function which is then differentiated and smoothed using the Savitzky-Golay filter. The optimal width of the filter is determined by minimization of the Integrated Square Error function. The current distribution of the TCSplin algorithm written in f77 with IDL and Gnuplot visualization scripts is available from http://www.virac.lv/en/soft.html
Spectral discrete probability density function of measured wind turbine noise in the far field.
Ashtiani, Payam; Denison, Adelaide
2015-01-01
Of interest is the spectral character of wind turbine noise at typical residential set-back distances. In this paper, a spectral statistical analysis has been applied to immission measurements conducted at three locations. This method provides discrete probability density functions for the Turbine ONLY component of the measured noise. This analysis is completed for one-third octave sound levels, at integer wind speeds, and is compared to existing metrics for measuring acoustic comfort as well as previous discussions on low-frequency noise sources.
Spectral discrete probability density function of measured wind turbine noise in the far field
Directory of Open Access Journals (Sweden)
Payam eAshtiani
2015-04-01
Full Text Available Of interest is the spectral character of wind turbine noise at typical residential set-back distances. In this paper a spectral statistical analysis has been applied to immission measurements conducted at three locations. This method provides discrete probability density functions for the Turbine ONLY component of the measured noise. This analysis is completed for 1/3rd Octave sound levels, at integer wind speeds, and is compared to existing metrics for measuring acoustic comfort as well as previous discussions on low frequency noise sources.
Directory of Open Access Journals (Sweden)
Aydın Kahriman
2011-11-01
Full Text Available Determine the diameter distribution of a stand and its relations with stand ages, site index, density and mixture percentage is very important both biologically and economically. The Weibull with two parameters, Weibull with three parameters, Gamma with two parameters, Gamma with three parameters, Beta, Lognormal with two parameters, Lognormal with three parameters, Normal, Johnson SB probability density functions were used to determination of diameter distributions. This study aimed to compared based on performance of describing different diameter distribution and to describe the best successful function of diameter distributions. The data were obtaited from 162 temporary sample plots measured Scots pine and Oriental beech mixed stands in Black Sea Region. The results show that four parameter Johnson SB function for both scots pine and oriental beech is the best successful function to describe diameter distributions based on error index values calculated by difference between observed and predicted diameter distributions.
Weatherbee, Andrew; Sugita, Mitsuro; Bizheva, Kostadinka; Popov, Ivan; Vitkin, Alex
2016-06-15
The distribution of backscattered intensities as described by the probability density function (PDF) of tissue-scattered light contains information that may be useful for tissue assessment and diagnosis, including characterization of its pathology. In this Letter, we examine the PDF description of the light scattering statistics in a well characterized tissue-like particulate medium using optical coherence tomography (OCT). It is shown that for low scatterer density, the governing statistics depart considerably from a Gaussian description and follow the K distribution for both OCT amplitude and intensity. The PDF formalism is shown to be independent of the scatterer flow conditions; this is expected from theory, and suggests robustness and motion independence of the OCT amplitude (and OCT intensity) PDF metrics in the context of potential biomedical applications.
Schneider, N; Csengeri, T; Klessen, R; Federrath, C; Tremblin, P; Girichidis, P; Bontemps, S; Andre, Ph
2014-01-01
Column density maps of molecular clouds are one of the most important observables in the context of molecular cloud- and star-formation (SF) studies. With Herschel it is now possible to reveal rather precisely the column density of dust, which is the best tracer of the bulk of material in molecular clouds. However, line-of-sight (LOS) contamination from fore- or background clouds can lead to an overestimation of the dust emission of molecular clouds, in particular for distant clouds. This implies too high values for column density and mass, and a misleading interpretation of probability distribution functions (PDFs) of the column density. In this paper, we demonstrate by using observations and simulations how LOS contamination affects the PDF. We apply a first-order approximation (removing a constant level) to the molecular clouds of Auriga and Maddalena (low-mass star-forming), and Carina and NGC3603(both high-mass SF regions). In perfect agreement with the simulations, we find that the PDFs become broader, ...
Firing statistics of inhibitory neuron with delayed feedback. I. Output ISI probability density.
Vidybida, A K; Kravchuk, K G
2013-06-01
Activity of inhibitory neuron with delayed feedback is considered in the framework of point stochastic processes. The neuron receives excitatory input impulses from a Poisson stream, and inhibitory impulses from the feedback line with a delay. We investigate here, how does the presence of inhibitory feedback affect the output firing statistics. Using binding neuron (BN) as a model, we derive analytically the exact expressions for the output interspike intervals (ISI) probability density, mean output ISI and coefficient of variation as functions of model's parameters for the case of threshold 2. Using the leaky integrate-and-fire (LIF) model, as well as the BN model with higher thresholds, these statistical quantities are found numerically. In contrast to the previously studied situation of no feedback, the ISI probability densities found here both for BN and LIF neuron become bimodal and have discontinuity of jump type. Nevertheless, the presence of inhibitory delayed feedback was not found to affect substantially the output ISI coefficient of variation. The ISI coefficient of variation found ranges between 0.5 and 1. It is concluded that introduction of delayed inhibitory feedback can radically change neuronal output firing statistics. This statistics is as well distinct from what was found previously (Vidybida and Kravchuk, 2009) by a similar method for excitatory neuron with delayed feedback.
Directory of Open Access Journals (Sweden)
Han Liwei
2014-07-01
Full Text Available Monitoring data on an earth-rockfill dam constitutes a form of spatial data. Such data include much uncertainty owing to the limitation of measurement information, material parameters, load, geometry size, initial conditions, boundary conditions and the calculation model. So the cloud probability density of the monitoring data must be addressed. In this paper, the cloud theory model was used to address the uncertainty transition between the qualitative concept and the quantitative description. Then an improved algorithm of cloud probability distribution density based on a backward cloud generator was proposed. This was used to effectively convert certain parcels of accurate data into concepts which can be described by proper qualitative linguistic values. Such qualitative description was addressed as cloud numerical characteristics-- {Ex, En, He}, which could represent the characteristics of all cloud drops. The algorithm was then applied to analyze the observation data of a piezometric tube in an earth-rockfill dam. And experiment results proved that the proposed algorithm was feasible, through which, we could reveal the changing regularity of piezometric tube’s water level. And the damage of the seepage in the body was able to be found out.
A Priori Knowledge and Probability Density Based Segmentation Method for Medical CT Image Sequences
Directory of Open Access Journals (Sweden)
Huiyan Jiang
2014-01-01
Full Text Available This paper briefly introduces a novel segmentation strategy for CT images sequences. As first step of our strategy, we extract a priori intensity statistical information from object region which is manually segmented by radiologists. Then we define a search scope for object and calculate probability density for each pixel in the scope using a voting mechanism. Moreover, we generate an optimal initial level set contour based on a priori shape of object of previous slice. Finally the modified distance regularity level set method utilizes boundaries feature and probability density to conform final object. The main contributions of this paper are as follows: a priori knowledge is effectively used to guide the determination of objects and a modified distance regularization level set method can accurately extract actual contour of object in a short time. The proposed method is compared to other seven state-of-the-art medical image segmentation methods on abdominal CT image sequences datasets. The evaluated results demonstrate our method performs better and has the potential for segmentation in CT image sequences.
Boslough, M.
2011-12-01
Climate-related uncertainty is traditionally presented as an error bar, but it is becoming increasingly common to express it in terms of a probability density function (PDF). PDFs are a necessary component of probabilistic risk assessments, for which simple "best estimate" values are insufficient. Many groups have generated PDFs for climate sensitivity using a variety of methods. These PDFs are broadly consistent, but vary significantly in their details. One axiom of the verification and validation community is, "codes don't make predictions, people make predictions." This is a statement of the fact that subject domain experts generate results using assumptions within a range of epistemic uncertainty and interpret them according to their expert opinion. Different experts with different methods will arrive at different PDFs. For effective decision support, a single consensus PDF would be useful. We suggest that market methods can be used to aggregate an ensemble of opinions into a single distribution that expresses the consensus. Prediction markets have been shown to be highly successful at forecasting the outcome of events ranging from elections to box office returns. In prediction markets, traders can take a position on whether some future event will or will not occur. These positions are expressed as contracts that are traded in a double-action market that aggregates price, which can be interpreted as a consensus probability that the event will take place. Since climate sensitivity cannot directly be measured, it cannot be predicted. However, the changes in global mean surface temperature are a direct consequence of climate sensitivity, changes in forcing, and internal variability. Viable prediction markets require an undisputed event outcome on a specific date. Climate-related markets exist on Intrade.com, an online trading exchange. One such contract is titled "Global Temperature Anomaly for Dec 2011 to be greater than 0.65 Degrees C." Settlement is based
Riggs, Peter J.
2013-01-01
Students often wrestle unsuccessfully with the task of correctly calculating momentum probability densities and have difficulty in understanding their interpretation. In the case of a particle in an "infinite" potential well, its momentum can take values that are not just those corresponding to the particle's quantised energies but…
A probability density function of liftoff velocities in mixed-size wind sand flux
Institute of Scientific and Technical Information of China (English)
2008-01-01
With the discrete element method(DEM) ,employing the diameter distribution of natural sands sampled from the Tengger Desert,a mixed-size sand bed was produced and the particle-bed collision was simulated in the mixed-size wind sand movement. In the simulation,the shear wind velocity,particle diameter,incident velocity and incident angle of the impact sand particle were given the same values as the experimental results. After the particle-bed collision,we collected all the initial velocities of rising sand particles,including the liftoff angular velocities,liftoff linear velocities and their horizontal and vertical components. By the statistical analysis on the velocity sample for each velocity component,its probability density functions were obtained,and they are the functions of the shear wind velocity. The liftoff velocities and their horizontal and vertical components are distributed as an exponential density function,while the angular velocities are distributed as a normal density function.
Institute of Scientific and Technical Information of China (English)
Wu Xinhui; Huang Gaoming; Gao Jun
2013-01-01
In Bayesian multi-target filtering, knowledge of measurement noise variance is very important. Significant mismatches in noise parameters will result in biased estimates. In this paper, a new particle filter for a probability hypothesis density (PHD) filter handling unknown measure-ment noise variances is proposed. The approach is based on marginalizing the unknown parameters out of the posterior distribution by using variational Bayesian (VB) methods. Moreover, the sequential Monte Carlo method is used to approximate the posterior intensity considering non-lin-ear and non-Gaussian conditions. Unlike other particle filters for this challenging class of PHD fil-ters, the proposed method can adaptively learn the unknown and time-varying noise variances while filtering. Simulation results show that the proposed method improves estimation accuracy in terms of both the number of targets and their states.
Sliding-mode control design for nonlinear systems using probability density function shaping.
Liu, Yu; Wang, Hong; Hou, Chaohuan
2014-02-01
In this paper, we propose a sliding-mode-based stochastic distribution control algorithm for nonlinear systems, where the sliding-mode controller is designed to stabilize the stochastic system and stochastic distribution control tries to shape the sliding surface as close as possible to the desired probability density function. Kullback-Leibler divergence is introduced to the stochastic distribution control, and the parameter of the stochastic distribution controller is updated at each sample interval rather than using a batch mode. It is shown that the estimated weight vector will converge to its ideal value and the system will be asymptotically stable under the rank-condition, which is much weaker than the persistent excitation condition. The effectiveness of the proposed algorithm is illustrated by simulation.
Evaluate the Word Error Rate of Binary Block Codes with Square Radius Probability Density Function
Chen, Xiaogang; Gu, Jian; Yang, Hongkui
2007-01-01
The word error rate (WER) of soft-decision-decoded binary block codes rarely has closed-form. Bounding techniques are widely used to evaluate the performance of maximum-likelihood decoding algorithm. But the existing bounds are not tight enough especially for low signal-to-noise ratios and become looser when a suboptimum decoding algorithm is used. This paper proposes a new concept named square radius probability density function (SR-PDF) of decision region to evaluate the WER. Based on the SR-PDF, The WER of binary block codes can be calculated precisely for ML and suboptimum decoders. Furthermore, for a long binary block code, SR-PDF can be approximated by Gamma distribution with only two parameters that can be measured easily. Using this property, two closed-form approximative expressions are proposed which are very close to the simulation results of the WER of interesting.
Palma, G
2009-01-01
The probability density function (PDF) of some global average quantity plays a fundamental role in critical and highly correlated systems. We explicitly compute this quantity as a function of the magnetization for the two dimensional XY model in its harmonic approximation. Numerical simulations and perturbative results have shown a Gumbel-like shape of the PDF, in spite of the fact that the average magnetization is not an extreme variable. Our analytical result allows to test both perturbative analytical expansions and also numerical computations performed previously. Perfect agreement is found for the first moments of the PDF. Also for large volume and in the high temperature limit the distribution becomes Gaussian, as it should be. In the low temperature regime its numerical evaluation is compatible with a Gumbel distribution.
Bakosi, J; Boybeyi, Z; 10.1063/1.2803348
2010-01-01
Dispersion of a passive scalar from concentrated sources in fully developed turbulent channel flow is studied with the probability density function (PDF) method. The joint PDF of velocity, turbulent frequency and scalar concentration is represented by a large number of Lagrangian particles. A stochastic near-wall PDF model combines the generalized Langevin model of Haworth & Pope with Durbin's method of elliptic relaxation to provide a mathematically exact treatment of convective and viscous transport with a non-local representation of the near-wall Reynolds stress anisotropy. The presence of walls is incorporated through the imposition of no-slip and impermeability conditions on particles without the use of damping or wall-functions. Information on the turbulent timescale is supplied by the gamma-distribution model of van Slooten et al. Two different micromixing models are compared that incorporate the effect of small scale mixing on the transported scalar: the widely used interaction by exchange with th...
The use of the compound probability density function in ultrasonic tissue characterization
Energy Technology Data Exchange (ETDEWEB)
Shankar, P M [Department of Electrical and Computer Engineering, Drexel University, 3141 Chestnut Street, Philadelphia, PA 19104 (United States)
2004-03-21
Recently, a compound probability density function (pdf) was proposed to model the envelope of the ultrasonic backscattered echo from tissues. This pdf will allow local and global variations in scattering cross sections and even multiple scattering in tissue. It approximates to the Nakagami, K or Rayleigh distributions under different limiting conditions, thus making it very versatile. In this work, a new parameter associated with compound pdf, speckle factor, has been introduced to characterize the scattering conditions. The usefulness of this parameter for tissue characterization has been explored through computer simulation of ultrasonic A scans and analyses of the data collected from tissue-mimicking phantoms. Results suggest the potential applications of the compound pdf and its parameters in ultrasonic tissue characterization.
Cavuoti, Stefano; Brescia, Massimo; Vellucci, Civita; Tortora, Crescenzo; Longo, Giuseppe
2016-01-01
A variety of fundamental astrophysical science topics require the determination of very accurate photometric redshifts (photo-z's). A wide plethora of methods have been developed, based either on template models fitting or on empirical explorations of the photometric parameter space. Machine learning based techniques are not explicitly dependent on the physical priors and able to produce accurate photo-z estimations within the photometric ranges derived from the spectroscopic training set. These estimates, however, are not easy to characterize in terms of a photo-z Probability Density Function (PDF), due to the fact that the analytical relation mapping the photometric parameters onto the redshift space is virtually unknown. We present METAPHOR (Machine-learning Estimation Tool for Accurate PHOtometric Redshifts), a method designed to provide a reliable PDF of the error distribution for empirical techniques. The method is implemented as a modular workflow, whose internal engine for photo-z estimation makes use...
Sadeh, Iftach; Lahav, Ofer
2015-01-01
We present ANNz2, a new implementation of the public software for photometric redshift (photo-z) estimation of Collister and Lahav (2004). Large photometric galaxy surveys are important for cosmological studies, and in particular for characterizing the nature of dark energy. The success of such surveys greatly depends on the ability to measure photo-zs, based on limited spectral data. ANNz2 utilizes multiple machine learning methods, such as artificial neural networks, boosted decision/regression trees and k-nearest neighbours. The objective of the algorithm is to dynamically optimize the performance of the photo-z estimation, and to properly derive the associated uncertainties. In addition to single-value solutions, the new code also generates full probability density functions (PDFs) in two different ways. In addition, estimators are incorporated to mitigate possible problems of spectroscopic training samples which are not representative or are incomplete. ANNz2 is also adapted to provide optimized solution...
Directory of Open Access Journals (Sweden)
Osmar Abílio de Carvalho Júnior
2014-04-01
Full Text Available Speckle noise (salt and pepper is inherent to synthetic aperture radar (SAR, which causes a usual noise-like granular aspect and complicates the image classification. In SAR image analysis, the spatial information might be a particular benefit for denoising and mapping classes characterized by a statistical distribution of the pixel intensities from a complex and heterogeneous spectral response. This paper proposes the Probability Density Components Analysis (PDCA, a new alternative that combines filtering and frequency histogram to improve the classification procedure for the single-channel synthetic aperture radar (SAR images. This method was tested on L-band SAR data from the Advanced Land Observation System (ALOS Phased-Array Synthetic-Aperture Radar (PALSAR sensor. The study area is localized in the Brazilian Amazon rainforest, northern Rondônia State (municipality of Candeias do Jamari, containing forest and land use patterns. The proposed algorithm uses a moving window over the image, estimating the probability density curve in different image components. Therefore, a single input image generates an output with multi-components. Initially the multi-components should be treated by noise-reduction methods, such as maximum noise fraction (MNF or noise-adjusted principal components (NAPCs. Both methods enable reducing noise as well as the ordering of multi-component data in terms of the image quality. In this paper, the NAPC applied to multi-components provided large reductions in the noise levels, and the color composites considering the first NAPC enhance the classification of different surface features. In the spectral classification, the Spectral Correlation Mapper and Minimum Distance were used. The results obtained presented as similar to the visual interpretation of optical images from TM-Landsat and Google Maps.
Fading probability density function of free-space optical communication channels with pointing error
Zhao, Zhijun; Liao, Rui
2011-06-01
The turbulent atmosphere causes wavefront distortion, beam wander, and beam broadening of a laser beam. These effects result in average power loss and instantaneous power fading at the receiver aperture and thus degrade performance of a free-space optical (FSO) communication system. In addition to the atmospheric turbulence, a FSO communication system may also suffer from laser beam pointing error. The pointing error causes excessive power loss and power fading. This paper proposes and studies an analytical method for calculating the FSO channel fading probability density function (pdf) induced by both atmospheric turbulence and pointing error. This method is based on the fast-tracked laser beam fading profile and the joint effects of beam wander and pointing error. In order to evaluate the proposed analytical method, large-scale numerical wave-optics simulations are conducted. Three types of pointing errors are studied , namely, the Gaussian random pointing error, the residual tracking error, and the sinusoidal sway pointing error. The FSO system employs a collimated Gaussian laser beam propagating along a horizontal path. The propagation distances range from 0.25 miles to 2.5 miles. The refractive index structure parameter is chosen to be Cn2 = 5×10-15m-2/3 and Cn2 = 5×10-13m-2/3. The studied cases cover from weak to strong fluctuations. The fading pdf curves of channels with pointing error calculated using the analytical method match accurately the corresponding pdf curves obtained directly from large-scale wave-optics simulations. They also give accurate average bit-error-rate (BER) curves and outage probabilities. Both the lognormal and the best-fit gamma-gamma fading pdf curves deviate from those of corresponding simulation curves, and they produce overoptimistic average BER curves and outage probabilities.
Molini, Annalisa; Katul, Gabriel; Porporato, Amilcare
2010-05-01
Possible linkages between climatic fluctuations in rainfall at low frequencies and local intensity fluctuations within single storms is now receiving significant attention in climate change research. To progress on a narrower scope of this problem, the cross-scale probabilistic structure of rainfall intensity records collected over time scales ranging from hours to decades at sites dominated by either convective or frontal systems is investigated. Across these sites, intermittency buildup from slow to fast time-scales is analyzed in terms of its heavy tailed and asymmetric signatures in the scale-wise evolution of rainfall probability density functions (pdfs). The analysis demonstrates that rainfall records dominated by convective storms develop heavier-tailed power law pdfs across finer scales when compared with their frontal systems counterpart. A concomitant marked asymmetry buildup also emerges across finer time scales necessitating skewed probability laws for quantifying the scale-wise evolution of rainfall pdfs. A scale-dependent probabilistic description of such fat tails, peakedness and asymmetry appearance is proposed and tested by using a modified q-Gaussian model, able to describe the scale wise evolution of rainfall pdfs in terms of the nonextensivity parameter q, a lacunarity (intermittency) correction γ and a tail asymmetry coefficient c, also functions of q.
Directory of Open Access Journals (Sweden)
Emilio Gómez-Lázaro
2016-02-01
Full Text Available The Weibull probability distribution has been widely applied to characterize wind speeds for wind energy resources. Wind power generation modeling is different, however, due in particular to power curve limitations, wind turbine control methods, and transmission system operation requirements. These differences are even greater for aggregated wind power generation in power systems with high wind penetration. Consequently, models based on one-Weibull component can provide poor characterizations for aggregated wind power generation. With this aim, the present paper focuses on discussing Weibull mixtures to characterize the probability density function (PDF for aggregated wind power generation. PDFs of wind power data are firstly classified attending to hourly and seasonal patterns. The selection of the number of components in the mixture is analyzed through two well-known different criteria: the Akaike information criterion (AIC and the Bayesian information criterion (BIC. Finally, the optimal number of Weibull components for maximum likelihood is explored for the defined patterns, including the estimated weight, scale, and shape parameters. Results show that multi-Weibull models are more suitable to characterize aggregated wind power data due to the impact of distributed generation, variety of wind speed values and wind power curtailment.
Development and evaluation of probability density functions for a set of human exposure factors
Energy Technology Data Exchange (ETDEWEB)
Maddalena, R.L.; McKone, T.E.; Bodnar, A.; Jacobson, J.
1999-06-01
The purpose of this report is to describe efforts carried out during 1998 and 1999 at the Lawrence Berkeley National Laboratory to assist the U.S. EPA in developing and ranking the robustness of a set of default probability distributions for exposure assessment factors. Among the current needs of the exposure-assessment community is the need to provide data for linking exposure, dose, and health information in ways that improve environmental surveillance, improve predictive models, and enhance risk assessment and risk management (NAS, 1994). The U.S. Environmental Protection Agency (EPA) Office of Emergency and Remedial Response (OERR) plays a lead role in developing national guidance and planning future activities that support the EPA Superfund Program. OERR is in the process of updating its 1989 Risk Assessment Guidance for Superfund (RAGS) as part of the EPA Superfund reform activities. Volume III of RAGS, when completed in 1999 will provide guidance for conducting probabilistic risk assessments. This revised document will contain technical information including probability density functions (PDFs) and methods used to develop and evaluate these PDFs. The PDFs provided in this EPA document are limited to those relating to exposure factors.
Measuring and Modeling Fault Density for Plume-Fault Encounter Probability Estimation
Energy Technology Data Exchange (ETDEWEB)
Jordan, P.D.; Oldenburg, C.M.; Nicot, J.-P.
2011-05-15
Emission of carbon dioxide from fossil-fueled power generation stations contributes to global climate change. Storage of this carbon dioxide within the pores of geologic strata (geologic carbon storage) is one approach to mitigating the climate change that would otherwise occur. The large storage volume needed for this mitigation requires injection into brine-filled pore space in reservoir strata overlain by cap rocks. One of the main concerns of storage in such rocks is leakage via faults. In the early stages of site selection, site-specific fault coverages are often not available. This necessitates a method for using available fault data to develop an estimate of the likelihood of injected carbon dioxide encountering and migrating up a fault, primarily due to buoyancy. Fault population statistics provide one of the main inputs to calculate the encounter probability. Previous fault population statistics work is shown to be applicable to areal fault density statistics. This result is applied to a case study in the southern portion of the San Joaquin Basin with the result that the probability of a carbon dioxide plume from a previously planned injection had a 3% chance of encountering a fully seal offsetting fault.
Tygert, Mark
2010-09-21
We discuss several tests for determining whether a given set of independent and identically distributed (i.i.d.) draws does not come from a specified probability density function. The most commonly used are Kolmogorov-Smirnov tests, particularly Kuiper's variant, which focus on discrepancies between the cumulative distribution function for the specified probability density and the empirical cumulative distribution function for the given set of i.i.d. draws. Unfortunately, variations in the probability density function often get smoothed over in the cumulative distribution function, making it difficult to detect discrepancies in regions where the probability density is small in comparison with its values in surrounding regions. We discuss tests without this deficiency, complementing the classical methods. The tests of the present paper are based on the plain fact that it is unlikely to draw a random number whose probability is small, provided that the draw is taken from the same distribution used in calculating the probability (thus, if we draw a random number whose probability is small, then we can be confident that we did not draw the number from the same distribution used in calculating the probability).
Robust functional statistics applied to Probability Density Function shape screening of sEMG data.
Boudaoud, S; Rix, H; Al Harrach, M; Marin, F
2014-01-01
Recent studies pointed out possible shape modifications of the Probability Density Function (PDF) of surface electromyographical (sEMG) data according to several contexts like fatigue and muscle force increase. Following this idea, criteria have been proposed to monitor these shape modifications mainly using High Order Statistics (HOS) parameters like skewness and kurtosis. In experimental conditions, these parameters are confronted with small sample size in the estimation process. This small sample size induces errors in the estimated HOS parameters restraining real-time and precise sEMG PDF shape monitoring. Recently, a functional formalism, the Core Shape Model (CSM), has been used to analyse shape modifications of PDF curves. In this work, taking inspiration from CSM method, robust functional statistics are proposed to emulate both skewness and kurtosis behaviors. These functional statistics combine both kernel density estimation and PDF shape distances to evaluate shape modifications even in presence of small sample size. Then, the proposed statistics are tested, using Monte Carlo simulations, on both normal and Log-normal PDFs that mimic observed sEMG PDF shape behavior during muscle contraction. According to the obtained results, the functional statistics seem to be more robust than HOS parameters to small sample size effect and more accurate in sEMG PDF shape screening applications.
Lussana, C.
2013-04-01
The presented work focuses on the investigation of gridded daily minimum (TN) and maximum (TX) temperature probability density functions (PDFs) with the intent of both characterising a region and detecting extreme values. The empirical PDFs estimation procedure has been realised using the most recent years of gridded temperature analysis fields available at ARPA Lombardia, in Northern Italy. The spatial interpolation is based on an implementation of Optimal Interpolation using observations from a dense surface network of automated weather stations. An effort has been made to identify both the time period and the spatial areas with a stable data density otherwise the elaboration could be influenced by the unsettled station distribution. The PDF used in this study is based on the Gaussian distribution, nevertheless it is designed to have an asymmetrical (skewed) shape in order to enable distinction between warming and cooling events. Once properly defined the occurrence of extreme events, it is possible to straightforwardly deliver to the users the information on a local-scale in a concise way, such as: TX extremely cold/hot or TN extremely cold/hot.
Zhu, Yu; Liu, Xiaojun; Gao, Jie; Zhang, Yixin; Zhao, Fengsheng
2014-04-07
We develop a novel model of the probability density of the orbital angular momentum (OAM) modes for Hankel-Bessel beams in paraxial turbulence channel based on the Rytov approximation. The results show that there are multi-peaks of the mode probability density along the radial direction. The peak position of the mode probability density moves to beam center with the increasing of non-Kolmogorov turbulence-parameters and the generalized refractive-index structure parameters and with the decreasing of OAM quantum number, propagation distance and wavelength of the beams. Additionally, larger OAM quantum number and smaller non-Kolmogorov turbulence-parameter can be selected in order to obtain larger mode probability density. The probability density of the OAM mode crosstalk is increasing with the decreasing of the quantum number deviation and the wavelength. Because of the focusing properties of Hankel-Bessel beams in turbulence channel, compared with the Laguerre-Gaussian beams, Hankel-Bessel beams are a good light source for weakening turbulence spreading of the beams and mitigating the effects of turbulence on the probability density of the OAM mode.
Representation of layer-counted proxy records as probability densities on error-free time axes
Boers, Niklas; Goswami, Bedartha; Ghil, Michael
2016-04-01
Time series derived from paleoclimatic proxy records exhibit substantial dating uncertainties in addition to the measurement errors of the proxy values. For radiometrically dated proxy archives, Goswami et al. [1] have recently introduced a framework rooted in Bayesian statistics that successfully propagates the dating uncertainties from the time axis to the proxy axis. The resulting proxy record consists of a sequence of probability densities over the proxy values, conditioned on prescribed age values. One of the major benefits of this approach is that the proxy record is represented on an accurate, error-free time axis. Such unambiguous dating is crucial, for instance, in comparing different proxy records. This approach, however, is not directly applicable to proxy records with layer-counted chronologies, as for example ice cores, which are typically dated by counting quasi-annually deposited ice layers. Hence the nature of the chronological uncertainty in such records is fundamentally different from that in radiometrically dated ones. Here, we introduce a modification of the Goswami et al. [1] approach that is specifically designed for layer-counted proxy records, instead of radiometrically dated ones. We apply our method to isotope ratios and dust concentrations in the NGRIP core, using a published 60,000-year chronology [2]. It is shown that the further one goes into the past, the more the layer-counting errors accumulate and lead to growing uncertainties in the probability density sequence for the proxy values that results from the proposed approach. For the older parts of the record, these uncertainties affect more and more a statistically sound estimation of proxy values. This difficulty implies that great care has to be exercised when comparing and in particular aligning specific events among different layer-counted proxy records. On the other hand, when attempting to derive stochastic dynamical models from the proxy records, one is only interested in the
Lu, C.; Liu, Y.; Niu, S.; Vogelmann, A. M.
2012-12-01
In situ aircraft cumulus observations from the RACORO field campaign are used to estimate entrainment rate for individual clouds using a recently developed mixing fraction approach. The entrainment rate is computed based on the observed state of the cloud core and the state of the air that is laterally mixed into the cloud at its edge. The computed entrainment rate decreases when the air is entrained from increasing distance from the cloud core edge; this is because the air farther away from cloud edge is drier than the neighboring air that is within the humid shells around cumulus clouds. Probability density functions of entrainment rate are well fitted by lognormal distributions at different heights above cloud base for different dry air sources (i.e., different source distances from the cloud core edge). Such lognormal distribution functions are appropriate for inclusion into future entrainment rate parameterization in large scale models. To the authors' knowledge, this is the first time that probability density functions of entrainment rate have been obtained in shallow cumulus clouds based on in situ observations. The reason for the wide spread of entrainment rate is that the observed clouds are affected by entrainment mixing processes to different extents, which is verified by the relationships between the entrainment rate and cloud microphysics/dynamics. The entrainment rate is negatively correlated with liquid water content and cloud droplet number concentration due to the dilution and evaporation in entrainment mixing processes. The entrainment rate is positively correlated with relative dispersion (i.e., ratio of standard deviation to mean value) of liquid water content and droplet size distributions, consistent with the theoretical expectation that entrainment mixing processes are responsible for microphysics fluctuations and spectral broadening. The entrainment rate is negatively correlated with vertical velocity and dissipation rate because entrainment
Probability density function and estimation for error of digitized map coordinates in GIS
Institute of Scientific and Technical Information of China (English)
童小华; 刘大杰
2004-01-01
Traditionally, it is widely accepted that measurement error usually obeys the normal distribution. However, in this paper a new idea is proposed that the error in digitized data which is a major derived data source in GIS does not obey the normal distribution but the p-norm distribution with a determinate parameter. Assuming that the error is random and has the same statistical properties, the probability density function of the normal distribution,Laplace distribution and p-norm distribution are derived based on the arithmetic mean axiom, median axiom and pmedian axiom, which means that the normal distribution is only one of these distributions but not the least one.Based on this idea, distribution fitness tests such as Skewness and Kurtosis coefficient test, Pearson chi-square x2 test and Kolmogorov test for digitized data are conducted. The results show that the error in map digitization obeys the p-norm distribution whose parameter is close to 1.60. A least p-norm estimation and the least square estimation of digitized data are further analyzed, showing that the least p-norm adiustment is better than the least square adjustment for digitized data processing in GIS.
Probability density functions of the average and difference intensities of Friedel opposites.
Shmueli, U; Flack, H D
2010-11-01
Trigonometric series for the average (A) and difference (D) intensities of Friedel opposites were carefully rederived and were normalized to minimize their dependence on sin(theta)/lambda. Probability density functions (hereafter p.d.f.s) of these series were then derived by the Fourier method [Shmueli, Weiss, Kiefer & Wilson (1984). Acta Cryst. A40, 651-660] and their expressions, which admit any chemical composition of the unit-cell contents, were obtained for the space group P1. Histograms of A and D were then calculated for an assumed random-structure model and for 3135 Friedel pairs of a published solved crystal structure, and were compared with the p.d.f.s after the latter were scaled up to the histograms. Good agreement was obtained for the random-structure model and a qualitative one for the published solved structure. The results indicate that the residual discrepancy is mainly due to the presumed statistical independence of the p.d.f.'s characteristic function on the contributions of the interatomic vectors.
Myers, Adam D; Ball, Nicholas M
2009-01-01
The use of photometric redshifts in cosmology is increasing. Often, however these photo-zs are treated like spectroscopic observations, in that the peak of the photometric redshift, rather than the full probability density function (PDF), is used. This overlooks useful information inherent in the full PDF. We introduce a new real-space estimator for one of the most used cosmological statistics, the 2-point correlation function, that weights by the PDF of individual photometric objects in a manner that is optimal when Poisson statistics dominate. As our estimator does not bin based on the PDF peak it substantially enhances the clustering signal by usefully incorporating information from all photometric objects that overlap the redshift bin of interest. As a real-world application, we measure QSO clustering in the Sloan Digital Sky Survey (SDSS) and find that our estimator improves the clustering signal by a factor equivalent to increasing the survey size by a factor of 2 to 3. Our technique uses spectroscopic ...
Vertical Overlap of Probability Density Functions of Cloud and Precipitation Hydrometeors
Ovchinnikov, M.; Lim, K. S. S.; Larson, V. E.; Wong, M.; Thayer-Calder, K.; Ghan, S. J.
2016-12-01
Coarse-resolution climate models increasingly rely on probability density functions (PDFs) to represent subgrid-scale variability of prognostic variables. While PDFs characterize the horizontal variability, a separate treatment is needed to account for the vertical structure of clouds and precipitation. When sub-columns are drawn from these PDFs for microphysics or radiation parameterizations, appropriate vertical correlations must be enforced via PDF overlap specifications. This study evaluates the representation of PDF overlap in the Subgrid Importance Latin Hypercube Sampler (SILHS) employed in the assumed PDF turbulence and cloud scheme called the Cloud Layers Unified By Binormals (CLUBB). PDF overlap in CLUBB-SILHS simulations of continental and tropical oceanic deep convection is compared with overlap of PDF of various microphysics variables in cloud-resolving model (CRM) simulations of the same cases that explicitly predict the 3D structure of cloud and precipitation fields. CRM results show that PDF overlap varies significantly between different hydrometeor types, as well as between PDFs of mass and number mixing ratios for each species, - a distinction that the current SILHS implementation does not make. Specifically, faster falling species, such as rain and graupel, exhibit significantly higher vertical coherence in their distributions than slow falling cloud liquid and ice. Development of a PDF overlap treatment linked to hydrometeor properties, such as fall speeds, in addition to the currently implemented dependency on the turbulent convective length scale will be discussed.
Huang, Y X; Zhou, Q; Qiu, X; Shang, X D; Lu, Z M; Liu, and Y L
2014-01-01
In this paper, we introduce a new way to estimate the scaling parameter of a self-similar process by considering the maximum probability density function (pdf) of tis increments. We prove this for $H$-self-similar processes in general and experimentally investigate it for turbulent velocity and temperature increments. We consider turbulent velocity database from an experimental homogeneous and nearly isotropic turbulent channel flow, and temperature data set obtained near the sidewall of a Rayleigh-B\\'{e}nard convection cell, where the turbulent flow is driven by buoyancy. For the former database, it is found that the maximum value of increment pdf $p_{\\max}(\\tau)$ is in a good agreement with lognormal distribution. We also obtain a scaling exponent $\\alpha\\simeq 0.37$, which is consistent with the scaling exponent for the first-order structure function reported in other studies. For the latter one, we obtain a scaling exponent $\\alpha_{\\theta}\\simeq0.33$. This index value is consistent with the Kolmogorov-Ob...
On the method of logarithmic cumulants for parametric probability density function estimation.
Krylov, Vladimir A; Moser, Gabriele; Serpico, Sebastiano B; Zerubia, Josiane
2013-10-01
Parameter estimation of probability density functions is one of the major steps in the area of statistical image and signal processing. In this paper we explore several properties and limitations of the recently proposed method of logarithmic cumulants (MoLC) parameter estimation approach which is an alternative to the classical maximum likelihood (ML) and method of moments (MoM) approaches. We derive the general sufficient condition for a strong consistency of the MoLC estimates which represents an important asymptotic property of any statistical estimator. This result enables the demonstration of the strong consistency of MoLC estimates for a selection of widely used distribution families originating from (but not restricted to) synthetic aperture radar image processing. We then derive the analytical conditions of applicability of MoLC to samples for the distribution families in our selection. Finally, we conduct various synthetic and real data experiments to assess the comparative properties, applicability and small sample performance of MoLC notably for the generalized gamma and K families of distributions. Supervised image classification experiments are considered for medical ultrasound and remote-sensing SAR imagery. The obtained results suggest that MoLC is a feasible and computationally fast yet not universally applicable alternative to MoM. MoLC becomes especially useful when the direct ML approach turns out to be unfeasible.
Jian, Jhih-Wei; Elumalai, Pavadai; Pitti, Thejkiran; Wu, Chih Yuan; Tsai, Keng-Chang; Chang, Jeng-Yih; Peng, Hung-Pin; Yang, An-Suei
2016-01-01
Predicting ligand binding sites (LBSs) on protein structures, which are obtained either from experimental or computational methods, is a useful first step in functional annotation or structure-based drug design for the protein structures. In this work, the structure-based machine learning algorithm ISMBLab-LIG was developed to predict LBSs on protein surfaces with input attributes derived from the three-dimensional probability density maps of interacting atoms, which were reconstructed on the query protein surfaces and were relatively insensitive to local conformational variations of the tentative ligand binding sites. The prediction accuracy of the ISMBLab-LIG predictors is comparable to that of the best LBS predictors benchmarked on several well-established testing datasets. More importantly, the ISMBLab-LIG algorithm has substantial tolerance to the prediction uncertainties of computationally derived protein structure models. As such, the method is particularly useful for predicting LBSs not only on experimental protein structures without known LBS templates in the database but also on computationally predicted model protein structures with structural uncertainties in the tentative ligand binding sites. PMID:27513851
Energy Technology Data Exchange (ETDEWEB)
Ovchinnikov, Mikhail [Pacific Northwest National Laboratory, Richland Washington USA; Lim, Kyo-Sun Sunny [Pacific Northwest National Laboratory, Richland Washington USA; Korea Atomic Energy Research Institute, Daejeon Republic of Korea; Larson, Vincent E. [Department of Mathematical Sciences, University of Wisconsin-Milwaukee, Milwaukee Wisconsin USA; Wong, May [Pacific Northwest National Laboratory, Richland Washington USA; National Center for Atmospheric Research, Boulder Colorado USA; Thayer-Calder, Katherine [National Center for Atmospheric Research, Boulder Colorado USA; Ghan, Steven J. [Pacific Northwest National Laboratory, Richland Washington USA
2016-11-05
Coarse-resolution climate models increasingly rely on probability density functions (PDFs) to represent subgrid-scale variability of prognostic variables. While PDFs characterize the horizontal variability, a separate treatment is needed to account for the vertical structure of clouds and precipitation. When sub-columns are drawn from these PDFs for microphysics or radiation parameterizations, appropriate vertical correlations must be enforced via PDF overlap specifications. This study evaluates the representation of PDF overlap in the Subgrid Importance Latin Hypercube Sampler (SILHS) employed in the assumed PDF turbulence and cloud scheme called the Cloud Layers Unified By Binormals (CLUBB). PDF overlap in CLUBB-SILHS simulations of continental and tropical oceanic deep convection is compared with overlap of PDF of various microphysics variables in cloud-resolving model (CRM) simulations of the same cases that explicitly predict the 3D structure of cloud and precipitation fields. CRM results show that PDF overlap varies significantly between different hydrometeor types, as well as between PDFs of mass and number mixing ratios for each species, - a distinction that the current SILHS implementation does not make. In CRM simulations that explicitly resolve cloud and precipitation structures, faster falling species, such as rain and graupel, exhibit significantly higher coherence in their vertical distributions than slow falling cloud liquid and ice. These results suggest that to improve the overlap treatment in the sub-column generator, the PDF correlations need to depend on hydrometeor properties, such as fall speeds, in addition to the currently implemented dependency on the turbulent convective length scale.
Homogeneous clusters over India using probability density function of daily rainfall
Kulkarni, Ashwini
2017-07-01
The Indian landmass has been divided into homogeneous clusters by applying the cluster analysis to the probability density function of a century-long time series of daily summer monsoon (June through September) rainfall at 357 grids over India, each of approximately 100 km × 100 km. The analysis gives five clusters over Indian landmass; only cluster 5 happened to be the contiguous region and all other clusters are dispersed away which confirms the erratic behavior of daily rainfall over India. The area averaged seasonal rainfall over cluster 5 has a very strong relationship with Indian summer monsoon rainfall; also, the rainfall variability over this region is modulated by the most important mode of climate system, i.e., El Nino Southern Oscillation (ENSO). This cluster could be considered as the representative of the entire Indian landmass to examine monsoon variability. The two-sample Kolmogorov-Smirnov test supports that the cumulative distribution functions of daily rainfall over cluster 5 and India as a whole do not differ significantly. The clustering algorithm is also applied to two time epochs 1901-1975 and 1976-2010 to examine the possible changes in clusters in a recent warming period. The clusters are drastically different in two time periods. They are more dispersed in recent period implying the more erroneous distribution of daily rainfall in recent period.
A measurement-driven adaptive probability hypothesis density filter for multitarget tracking
Institute of Scientific and Technical Information of China (English)
Si Weijian; Wang Liwei; Qu Zhiyu
2015-01-01
This paper studies the dynamic estimation problem for multitarget tracking. A novel gat-ing strategy that is based on the measurement likelihood of the target state space is proposed to improve the overall effectiveness of the probability hypothesis density (PHD) filter. Firstly, a measurement-driven mechanism based on this gating technique is designed to classify the measure-ments. In this mechanism, only the measurements for the existing targets are considered in the update step of the existing targets while the measurements of newborn targets are used for exploring newborn targets. Secondly, the gating strategy enables the development of a heuristic state estima-tion algorithm when sequential Monte Carlo (SMC) implementation of the PHD filter is investi-gated, where the measurements are used to drive the particle clustering within the space gate. The resulting PHD filter can achieve a more robust and accurate estimation of the existing targets by reducing the interference from clutter. Moreover, the target birth intensity can be adaptive to detect newborn targets, which is in accordance with the birth measurements. Simulation results demonstrate the computational efficiency and tracking performance of the proposed algorithm. ? 2015 The Authors. Production and hosting by Elsevier Ltd. on behalf of CSAA&BUAA. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Representation of Probability Density Functions from Orbit Determination using the Particle Filter
Mashiku, Alinda K.; Garrison, James; Carpenter, J. Russell
2012-01-01
Statistical orbit determination enables us to obtain estimates of the state and the statistical information of its region of uncertainty. In order to obtain an accurate representation of the probability density function (PDF) that incorporates higher order statistical information, we propose the use of nonlinear estimation methods such as the Particle Filter. The Particle Filter (PF) is capable of providing a PDF representation of the state estimates whose accuracy is dependent on the number of particles or samples used. For this method to be applicable to real case scenarios, we need a way of accurately representing the PDF in a compressed manner with little information loss. Hence we propose using the Independent Component Analysis (ICA) as a non-Gaussian dimensional reduction method that is capable of maintaining higher order statistical information obtained using the PF. Methods such as the Principal Component Analysis (PCA) are based on utilizing up to second order statistics, hence will not suffice in maintaining maximum information content. Both the PCA and the ICA are applied to two scenarios that involve a highly eccentric orbit with a lower apriori uncertainty covariance and a less eccentric orbit with a higher a priori uncertainty covariance, to illustrate the capability of the ICA in relation to the PCA.
Nonparametric statistical methods
Hollander, Myles; Chicken, Eric
2013-01-01
Praise for the Second Edition"This book should be an essential part of the personal library of every practicing statistician."-Technometrics Thoroughly revised and updated, the new edition of Nonparametric Statistical Methods includes additional modern topics and procedures, more practical data sets, and new problems from real-life situations. The book continues to emphasize the importance of nonparametric methods as a significant branch of modern statistics and equips readers with the conceptual and technical skills necessary to select and apply the appropriate procedures for any given sit
Nonparametric Bayesian inference for multidimensional compound Poisson processes
S. Gugushvili; F. van der Meulen; P. Spreij
2015-01-01
Given a sample from a discretely observed multidimensional compound Poisson process, we study the problem of nonparametric estimation of its jump size density r0 and intensity λ0. We take a nonparametric Bayesian approach to the problem and determine posterior contraction rates in this context, whic
Coclite, A.; Pascazio, G.; De Palma, P.; Cutrone, L.
2016-07-01
Flamelet-Progress-Variable (FPV) combustion models allow the evaluation of all thermochemical quantities in a reacting flow by computing only the mixture fraction Z and a progress variable C. When using such a method to predict turbulent combustion in conjunction with a turbulence model, a probability density function (PDF) is required to evaluate statistical averages (e. g., Favre averages) of chemical quantities. The choice of the PDF is a compromise between computational costs and accuracy level. The aim of this paper is to investigate the influence of the PDF choice and its modeling aspects to predict turbulent combustion. Three different models are considered: the standard one, based on the choice of a β-distribution for Z and a Dirac-distribution for C; a model employing a β-distribution for both Z and C; and the third model obtained using a β-distribution for Z and the statistically most likely distribution (SMLD) for C. The standard model, although widely used, does not take into account the interaction between turbulence and chemical kinetics as well as the dependence of the progress variable not only on its mean but also on its variance. The SMLD approach establishes a systematic framework to incorporate informations from an arbitrary number of moments, thus providing an improvement over conventionally employed presumed PDF closure models. The rational behind the choice of the three PDFs is described in some details and the prediction capability of the corresponding models is tested vs. well-known test cases, namely, the Sandia flames, and H2-air supersonic combustion.
Cavuoti, S.; Amaro, V.; Brescia, M.; Vellucci, C.; Tortora, C.; Longo, G.
2017-02-01
A variety of fundamental astrophysical science topics require the determination of very accurate photometric redshifts (photo-z). A wide plethora of methods have been developed, based either on template models fitting or on empirical explorations of the photometric parameter space. Machine-learning-based techniques are not explicitly dependent on the physical priors and able to produce accurate photo-z estimations within the photometric ranges derived from the spectroscopic training set. These estimates, however, are not easy to characterize in terms of a photo-z probability density function (PDF), due to the fact that the analytical relation mapping the photometric parameters on to the redshift space is virtually unknown. We present METAPHOR (Machine-learning Estimation Tool for Accurate PHOtometric Redshifts), a method designed to provide a reliable PDF of the error distribution for empirical techniques. The method is implemented as a modular workflow, whose internal engine for photo-z estimation makes use of the MLPQNA neural network (Multi Layer Perceptron with Quasi Newton learning rule), with the possibility to easily replace the specific machine-learning model chosen to predict photo-z. We present a summary of results on SDSS-DR9 galaxy data, used also to perform a direct comparison with PDFs obtained by the LE PHARE spectral energy distribution template fitting. We show that METAPHOR is capable to estimate the precision and reliability of photometric redshifts obtained with three different self-adaptive techniques, i.e. MLPQNA, Random Forest and the standard K-Nearest Neighbors models.
Non-Parametric Tests of Structure for High Angular Resolution Diffusion Imaging in Q-Space
Olhede, Sofia C
2010-01-01
High angular resolution diffusion imaging data is the observed characteristic function for the local diffusion of water molecules in tissue. This data is used to infer structural information in brain imaging. Non-parametric scalar measures are proposed to summarize such data, and to locally characterize spatial features of the diffusion probability density function (PDF), relying on the geometry of the characteristic function. Summary statistics are defined so that their distributions are, to first order, both independent of nuisance parameters and also analytically tractable. The dominant direction of the diffusion at a spatial location (voxel) is determined, and a new set of axes are introduced in Fourier space. Variation quantified in these axes determines the local spatial properties of the diffusion density. Non-parametric hypothesis tests for determining whether the diffusion is unimodal, isotropic or multi-modal are proposed. More subtle characteristics of white-matter microstructure, such as the degre...
Nonparametric Bayesian inference in biostatistics
Müller, Peter
2015-01-01
As chapters in this book demonstrate, BNP has important uses in clinical sciences and inference for issues like unknown partitions in genomics. Nonparametric Bayesian approaches (BNP) play an ever expanding role in biostatistical inference from use in proteomics to clinical trials. Many research problems involve an abundance of data and require flexible and complex probability models beyond the traditional parametric approaches. As this book's expert contributors show, BNP approaches can be the answer. Survival Analysis, in particular survival regression, has traditionally used BNP, but BNP's potential is now very broad. This applies to important tasks like arrangement of patients into clinically meaningful subpopulations and segmenting the genome into functionally distinct regions. This book is designed to both review and introduce application areas for BNP. While existing books provide theoretical foundations, this book connects theory to practice through engaging examples and research questions. Chapters c...
van der Kleij, S.W.; Rispens, J.E.; Scheper, A.R.
2016-01-01
The aim of this study was to examine the influence of phonotactic probability (PP) and neighbourhood density (ND) on pseudoword learning in 17 Dutch-speaking typically developing children (mean age 7;2). They were familiarized with 16 one-syllable pseudowords varying in PP (high vs low) and ND (high
Kleij, S.W. van der; Rispens, J.E.; Scheper, A.R.
2016-01-01
The aim of this study was to examine the influence of phonotactic probability (PP) and neighbourhood density (ND) on pseudoword learning in 17 Dutch-speaking typically developing children (mean age 7; 2). They were familiarized with 16 one-syllable pseudowords varying in PP (high vs low) and ND
Nonparametric Predictive Regression
Ioannis Kasparis; Elena Andreou; Phillips, Peter C.B.
2012-01-01
A unifying framework for inference is developed in predictive regressions where the predictor has unknown integration properties and may be stationary or nonstationary. Two easily implemented nonparametric F-tests are proposed. The test statistics are related to those of Kasparis and Phillips (2012) and are obtained by kernel regression. The limit distribution of these predictive tests holds for a wide range of predictors including stationary as well as non-stationary fractional and near unit...
2nd Conference of the International Society for Nonparametric Statistics
Manteiga, Wenceslao; Romo, Juan
2016-01-01
This volume collects selected, peer-reviewed contributions from the 2nd Conference of the International Society for Nonparametric Statistics (ISNPS), held in Cádiz (Spain) between June 11–16 2014, and sponsored by the American Statistical Association, the Institute of Mathematical Statistics, the Bernoulli Society for Mathematical Statistics and Probability, the Journal of Nonparametric Statistics and Universidad Carlos III de Madrid. The 15 articles are a representative sample of the 336 contributed papers presented at the conference. They cover topics such as high-dimensional data modelling, inference for stochastic processes and for dependent data, nonparametric and goodness-of-fit testing, nonparametric curve estimation, object-oriented data analysis, and semiparametric inference. The aim of the ISNPS 2014 conference was to bring together recent advances and trends in several areas of nonparametric statistics in order to facilitate the exchange of research ideas, promote collaboration among researchers...
Pagnini, Gianni; Mura, Antonio; Mainardi, Francesco
2013-05-13
Two-particle dispersion is investigated in the context of anomalous diffusion. Two different modelling approaches related to time subordination are considered and unified in the framework of self-similar stochastic processes. By assuming a single-particle fractional Brownian motion and that the two-particle correlation function decreases in time with a power law, the particle relative separation density is computed for the cases with time sub-ordination directed by a unilateral M-Wright density and by an extremal Lévy stable density. Looking for advisable mathematical properties (for instance, the stationarity of the increments), the corresponding self-similar stochastic processes are represented in terms of fractional Brownian motions with stochastic variance, whose profile is modelled by using the M-Wright density or the Lévy stable density.
Bellin, Alberto; Tonina, Daniele
2007-10-30
Available models of solute transport in heterogeneous formations lack in providing complete characterization of the predicted concentration. This is a serious drawback especially in risk analysis where confidence intervals and probability of exceeding threshold values are required. Our contribution to fill this gap of knowledge is a probability distribution model for the local concentration of conservative tracers migrating in heterogeneous aquifers. Our model accounts for dilution, mechanical mixing within the sampling volume and spreading due to formation heterogeneity. It is developed by modeling local concentration dynamics with an Ito Stochastic Differential Equation (SDE) that under the hypothesis of statistical stationarity leads to the Beta probability distribution function (pdf) for the solute concentration. This model shows large flexibility in capturing the smoothing effect of the sampling volume and the associated reduction of the probability of exceeding large concentrations. Furthermore, it is fully characterized by the first two moments of the solute concentration, and these are the same pieces of information required for standard geostatistical techniques employing Normal or Log-Normal distributions. Additionally, we show that in the absence of pore-scale dispersion and for point concentrations the pdf model converges to the binary distribution of [Dagan, G., 1982. Stochastic modeling of groundwater flow by unconditional and conditional probabilities, 2, The solute transport. Water Resour. Res. 18 (4), 835-848.], while it approaches the Normal distribution for sampling volumes much larger than the characteristic scale of the aquifer heterogeneity. Furthermore, we demonstrate that the same model with the spatial moments replacing the statistical moments can be applied to estimate the proportion of the plume volume where solute concentrations are above or below critical thresholds. Application of this model to point and vertically averaged bromide
Nonparametric statistical inference
Gibbons, Jean Dickinson
2014-01-01
Thoroughly revised and reorganized, the fourth edition presents in-depth coverage of the theory and methods of the most widely used nonparametric procedures in statistical analysis and offers example applications appropriate for all areas of the social, behavioral, and life sciences. The book presents new material on the quantiles, the calculation of exact and simulated power, multiple comparisons, additional goodness-of-fit tests, methods of analysis of count data, and modern computer applications using MINITAB, SAS, and STATXACT. It includes tabular guides for simplified applications of tests and finding P values and confidence interval estimates.
Institute of Scientific and Technical Information of China (English)
Zeng Hong-Ling; Gao Xin-Quan; Zhang Wen
2005-01-01
In this paper the dryness/wetness (DW) grade data of the Yangtze River delta is transformed into the temporal evolution of precipitation probability (PP), and its hierarchically distributive characters are revealed. Research results show that the precipitation of the Yangtze River delta displays the interannual, interdecadal, as well as longer quasiperiodic changes than a century, and all the periods have a confidence level of more than 0.05. In the DW grade series of 530 years, although the frequency of the small probability events (SPEs) of drought/flood in each area of the Yangtze River delta is different, the frequency of the SPEs triggered by the climatic background state is yet the same. This research result fully shows the significant impact of the climatic evolution as a background state upon the occurrence of SPEs, which will be instructive in climatic prediction theory and in raising the accuracy of the climatic prediction.
Protein distance constraints predicted by neural networks and probability density functions
DEFF Research Database (Denmark)
Lund, Ole; Frimand, Kenneth; Gorodkin, Jan;
1997-01-01
We predict interatomic C-α distances by two independent data driven methods. The first method uses statistically derived probability distributions of the pairwise distance between two amino acids, whilst the latter method consists of a neural network prediction approach equipped with windows taki...... method based on the predicted distances is presented. A homepage with software, predictions and data related to this paper is available at http://www.cbs.dtu.dk/services/CPHmodels/...
Angraini, Lily Maysari; Suparmi, Variani, Viska Inda
2010-12-01
SUSY quantum mechanics can be applied to solve Schrodinger equation for high dimensional system that can be reduced into one dimensional system and represented in lowering and raising operators. Lowering and raising operators can be obtained using relationship between original Hamiltonian equation and the (super) potential equation. In this paper SUSY quantum mechanics is used as a method to obtain the wave function and the energy level of the Modified Poschl Teller potential. The graph of wave function equation and probability density is simulated by using Delphi 7.0 programming language. Finally, the expectation value of quantum mechanics operator could be calculated analytically using integral form or probability density graph resulted by the programming.
Nonparametric Bayesian Modeling for Automated Database Schema Matching
Energy Technology Data Exchange (ETDEWEB)
Ferragut, Erik M [ORNL; Laska, Jason A [ORNL
2015-01-01
The problem of merging databases arises in many government and commercial applications. Schema matching, a common first step, identifies equivalent fields between databases. We introduce a schema matching framework that builds nonparametric Bayesian models for each field and compares them by computing the probability that a single model could have generated both fields. Our experiments show that our method is more accurate and faster than the existing instance-based matching algorithms in part because of the use of nonparametric Bayesian models.
Complex Probability Distributions A Solution for the Long-Standing Problem of QCD at Finite Density
Azcoiti, V
1996-01-01
We show how the prescription of taking the absolute value of the fermion determinant in the integration measure of QCD at finite density, forgetting its phase, reproduces the correct thermodynamical limit. This prescription, which applies also to other gauge theories with non-positive-definite integration measure, also has the advantage of killing finite size effects due to extremely small mean values of the cosine of the phase of the fermion determinant. We also give an explanation for the pathological behaviour of quenched QCD at finite density.
Criticality of the net-baryon number probability distribution at finite density
Directory of Open Access Journals (Sweden)
Kenji Morita
2015-02-01
Full Text Available We compute the probability distribution P(N of the net-baryon number at finite temperature and quark-chemical potential, μ, at a physical value of the pion mass in the quark-meson model within the functional renormalization group scheme. For μ/T<1, the model exhibits the chiral crossover transition which belongs to the universality class of the O(4 spin system in three dimensions. We explore the influence of the chiral crossover transition on the properties of the net baryon number probability distribution, P(N. By considering ratios of P(N to the Skellam function, with the same mean and variance, we unravel the characteristic features of the distribution that are related to O(4 criticality at the chiral crossover transition. We explore the corresponding ratios for data obtained at RHIC by the STAR Collaboration and discuss their implications. We also examine O(4 criticality in the context of binomial and negative-binomial distributions for the net proton number.
Probability Density Estimation for Non-flat Functions%非平坦函数概率密度估计
Institute of Scientific and Technical Information of China (English)
汪洪桥; 蔡艳宁; 付光远; 王仕成
2016-01-01
Aiming at the probability density estimation problem for non-flat functions, this paper constructs a single slack factor multi-scale kernel support vector machine (SVM) probability density estimation model, by improving the form of constraint condition of the traditional SVM model and introducing the multi-scale kernel method. In the model, a single slack factor instead of two types of slack factors is used to control the learning error of SVM, which reduces the computational complexity of model. At the same time, by introducing the multi-scale kernel method, the model can well fit the functions with both the fiercely changed region and the flatly changed region. Through several probability density estimation experiments with typical non-flat functions, the results show that the single slack probability density estimation model has faster learning speed than the common SVM model. And compared with the single kernel method, the multi-scale kernel SVM probability density estimation model has better estimation precision.%针对非平坦函数的概率密度估计问题，通过改进支持向量机（support vector machine，SVM）概率密度估计模型约束条件的形式，并引入多尺度核方法，构建了一种单松弛因子多尺度核支持向量机概率密度估计模型。该模型采用合并的单个松弛因子来控制支持向量机的学习误差，减小了模型的计算复杂度；同时引入了多尺度核方法，使得模型既能适应函数剧烈变化的区域，也能适应平缓变化的区域。基于几种典型非平坦函数进行概率密度估计实验，结果证明，单松弛因子概率密度估计模型比常规支持向量机概率密度估计模型具有更快的学习速度；且相比于单核方法，多尺度核支持向量机概率密度估计模型具有更优的估计精度。
Probability density functions for the variable solar wind near the solar cycle minimum
Vörös,; Leitner, M; Narita, Y; Consolini, G; Kovács, P; Tóth, A; Lichtenberger, J
2015-01-01
Unconditional and conditional statistics is used for studying the histograms of magnetic field multi-scale fluctuations in the solar wind near the solar cycle minimum in 2008. The unconditional statistics involves the magnetic data during the whole year 2008. The conditional statistics involves the magnetic field time series splitted into concatenated subsets of data according to a threshold in dynamic pressure. The threshold separates fast stream leading edge compressional and trailing edge uncompressional fluctuations. The histograms obtained from these data sets are associated with both large-scale (B) and small-scale ({\\delta}B) magnetic fluctuations, the latter corresponding to time-delayed differences. It is shown here that, by keeping flexibility but avoiding the unnecessary redundancy in modeling, the histograms can be effectively described by a limited set of theoretical probability distribution functions (PDFs), such as the normal, log-normal, kappa and logkappa functions. In a statistical sense the...
Nonparametric Transient Classification using Adaptive Wavelets
Varughese, Melvin M; Stephanou, Michael; Bassett, Bruce A
2015-01-01
Classifying transients based on multi band light curves is a challenging but crucial problem in the era of GAIA and LSST since the sheer volume of transients will make spectroscopic classification unfeasible. Here we present a nonparametric classifier that uses the transient's light curve measurements to predict its class given training data. It implements two novel components: the first is the use of the BAGIDIS wavelet methodology - a characterization of functional data using hierarchical wavelet coefficients. The second novelty is the introduction of a ranked probability classifier on the wavelet coefficients that handles both the heteroscedasticity of the data in addition to the potential non-representativity of the training set. The ranked classifier is simple and quick to implement while a major advantage of the BAGIDIS wavelets is that they are translation invariant, hence they do not need the light curves to be aligned to extract features. Further, BAGIDIS is nonparametric so it can be used for blind ...
Directory of Open Access Journals (Sweden)
N. Hanekom
1991-09-01
Full Text Available Numbers of blue duikers recorded on 157 and 28 variable width transect counts, done over a two year period in the Tsitsikamma Coastal National Park (TCNP and Tsitsikamma Forest National Park (TFNP respectively, did not differ significantly {P > 0,10 with seasons (summer v. winter. Population density estimates from transects were similar to those from game drives (0,18 v. 0,19 duikers/ha (TCNP and 0,13 v. 0,17 duikers/ha (TFNP; P >0,10, higher than from faecal pellet counts (P < 0,10 and at least three times lower than estimates from the Kenneth Stainbank Nature Reserve and Umdoni Park in Natal. Factors contributing to the low population densities in the Tsitsikamma national parks were investigated. Twentyseven and seven percent of leopard (25 and caracal (12 scats respectively analyzed contained blue duiker remains, but predator numbers appear to be low. Forest characteristics were investigated, and results from this and other studies suggest that undergrowth cover does not markedly influence blue duiker densities in the southern Cape forests. Field and stomach analysis indicate that blue duikers feed primarily on freshly fallen leaves and fruit, and are selective foragers. In the Tsitsikamma national parks (TNPs the frequency of occurrence of trees known to be palatable to duikers are low, while less than 45 percent of the dominant tree species fruit fully annually. This apparent scarcity of food, the low numbers of antelope species and individuals in these forests and results from duiker research in Zaire, suggest that habitat rather than predation is limiting duiker numbers in the Tsitsikamma national parks.
Chowdhury, Shakhawat
2013-05-01
The evaluation of the status of a municipal drinking water treatment plant (WTP) is important. The evaluation depends on several factors, including, human health risks from disinfection by-products (R), disinfection performance (D), and cost (C) of water production and distribution. The Dempster-Shafer theory (DST) of evidence can combine the individual status with respect to R, D, and C to generate a new indicator, from which the overall status of a WTP can be evaluated. In the DST, the ranges of different factors affecting the overall status are divided into several segments. The basic probability assignments (BPA) for each segment of these factors are provided by multiple experts, which are then combined to obtain the overall status. In assigning the BPA, the experts use their individual judgments, which can impart subjective biases in the overall evaluation. In this research, an approach has been introduced to avoid the assignment of subjective BPA. The factors contributing to the overall status were characterized using the probability density functions (PDF). The cumulative probabilities for different segments of these factors were determined from the cumulative density function, which were then assigned as the BPA for these factors. A case study is presented to demonstrate the application of PDF in DST to evaluate a WTP, leading to the selection of the required level of upgradation for the WTP.
Nonparametric tests for censored data
Bagdonavicus, Vilijandas; Nikulin, Mikhail
2013-01-01
This book concerns testing hypotheses in non-parametric models. Generalizations of many non-parametric tests to the case of censored and truncated data are considered. Most of the test results are proved and real applications are illustrated using examples. Theories and exercises are provided. The incorrect use of many tests applying most statistical software is highlighted and discussed.
An extended SMLD approach for presumed probability density function in flamelet combustion model
Coclite, Alessandro; De Palma, Pietro; Cutrone, Luigi
2013-01-01
This paper provides an extension of the standard flamelet progress variable (FPV) approach for turbulent combustion, applying the statistically most likely distribution (SMLD) framework to the joint PDF of the mixture fraction, Z, and the progress variable, C. In this way one does not need to make any assumption about the statistical correlation between Z and C and about the behaviour of the mixture fraction, as required in previous FPV models. In fact, for state-of-the-art models, with the assumption of very-fast-chemistry,Z is widely accepted to behave as a passive scalar characterized by a $\\beta$-distribution function. Instead, the model proposed here, evaluates the most probable joint distribution of Z and C without any assumption on their behaviour and provides an effective tool to verify the adequateness of widely used hypotheses, such as their statistical independence. The model is validated versus three well-known test cases, namely, the Sandia flames. The results are compared with those obtained by ...
Yu, Zhi-wu; Mao, Jian-feng; Guo, Feng-qi; Guo, Wei
2016-03-01
Rail irregularity is one of the main sources causing train-bridge random vibration. A new random vibration theory for the coupled train-bridge systems is proposed in this paper. First, number theory method (NTM) with 2N-dimensional vectors for the stochastic harmonic function (SHF) of rail irregularity power spectrum density was adopted to determine the representative points of spatial frequencies and phases to generate the random rail irregularity samples, and the non-stationary rail irregularity samples were modulated with the slowly varying function. Second, the probability density evolution method (PDEM) was employed to calculate the random dynamic vibration of the three-dimensional (3D) train-bridge system by a program compiled on the MATLAB® software platform. Eventually, the Newmark-β integration method and double edge difference method of total variation diminishing (TVD) format were adopted to obtain the mean value curve, the standard deviation curve and the time-history probability density information of responses. A case study was presented in which the ICE-3 train travels on a three-span simply-supported high-speed railway bridge with excitation of random rail irregularity. The results showed that compared to the Monte Carlo simulation, the PDEM has higher computational efficiency for the same accuracy, i.e., an improvement by 1-2 orders of magnitude. Additionally, the influences of rail irregularity and train speed on the random vibration of the coupled train-bridge system were discussed.
Benda, L. E.
2009-12-01
Stochastic geomorphology refers to the interaction of the stochastic field of sediment supply with hierarchically branching river networks where erosion, sediment flux and storage are described by their probability densities. The conceptual and numerical framework can generate a series of general principles (hypotheses) on how basin-scale erosion and sedimentation regimes, viewed through the lens of probability distributions, change with variations in climate, topography, geology, vegetation, basin scale, and network topology; for more detail on the general principles see AGU session EP02. The conceptual and numerical framework of stochastic geomorphology is well suited for forecasting and interpreting affects of climate change on geomorphological systems, including the habitats associated with them. Climate change involves shifts in probability distributions of precipitation (rain and snow), fires, and wind. Consequently, shifts in distributions of precipitation frequency and magnitude or wildfire frequency, intensity and size should lead to shifts in erosion, sediment flux and sedimentation distributions. Shifts could include either a greater or lesser skew of their attendant probability densities. For example, increasing the frequency of fires in a stochastic simulation model of erosion and sedimentation will lead to altered frequency and magnitude of hillslope erosion in the form of pulses of sediment through the river network. This will be reflected in shifts in the probability densities of erosion and sedimentation and also how sediment flux and storage distributions evolve downstream in river networks. Heightened erosion frequency and magnitude due to climate change can increase Hurst Effects in time series of sediment flux and thus an increase in depletion of hillslope stores of sediment can result in temporally lingering sedimentation affects throughout river networks, even if climate relaxed to pre-change conditions. Similarly, heightened hillslope
Rediscovery of Good-Turing estimators via Bayesian nonparametrics.
Favaro, Stefano; Nipoti, Bernardo; Teh, Yee Whye
2016-03-01
The problem of estimating discovery probabilities originated in the context of statistical ecology, and in recent years it has become popular due to its frequent appearance in challenging applications arising in genetics, bioinformatics, linguistics, designs of experiments, machine learning, etc. A full range of statistical approaches, parametric and nonparametric as well as frequentist and Bayesian, has been proposed for estimating discovery probabilities. In this article, we investigate the relationships between the celebrated Good-Turing approach, which is a frequentist nonparametric approach developed in the 1940s, and a Bayesian nonparametric approach recently introduced in the literature. Specifically, under the assumption of a two parameter Poisson-Dirichlet prior, we show that Bayesian nonparametric estimators of discovery probabilities are asymptotically equivalent, for a large sample size, to suitably smoothed Good-Turing estimators. As a by-product of this result, we introduce and investigate a methodology for deriving exact and asymptotic credible intervals to be associated with the Bayesian nonparametric estimators of discovery probabilities. The proposed methodology is illustrated through a comprehensive simulation study and the analysis of Expressed Sequence Tags data generated by sequencing a benchmark complementary DNA library.
Nitsche, Ludwig C.; Nitsche, Johannes M.; Brenner, Howard
1988-01-01
The sedimentation and diffusion of a nonneutrally buoyant Brownian particle in vertical fluid-filled cylinder of finite length which is instantaneously inverted at regular intervals are investigated analytically. A one-dimensional convective-diffusive equation is derived to describe the temporal and spatial evolution of the probability density; a periodicity condition is formulated; the applicability of Fredholm theory is established; and the parameter-space regions are determined within which the existence and uniqueness of solutions are guaranteed. Numerical results for sample problems are presented graphically and briefly characterized.
Rius, Jordi
2006-09-01
The maximum-likelihood method is applied to direct methods to derive a more general probability density function of the triple-phase sums which is capable of predicting negative values. This study also proves that maximization of the origin-free modulus sum function S yields, within the limitations imposed by the assumed approximations, the maximum-likelihood estimates of the phases. It thus represents the formal theoretical justification of the S function that was initially derived from Patterson-function arguments [Rius (1993). Acta Cryst. A49, 406-409].
Lopes Cardozo, David; Holdsworth, Peter C. W.
2016-04-01
The magnetization probability density in d = 2 and 3 dimensional Ising models in slab geometry of volume L\\paralleld-1× {{L}\\bot} is computed through Monte-Carlo simulation at the critical temperature and zero magnetic field. The finite-size scaling of this distribution and its dependence on the system aspect-ratio ρ =\\frac{{{L}\\bot}}{{{L}\\parallel}} and boundary conditions are discussed. In the limiting case ρ \\to 0 of a macroscopically large slab ({{L}\\parallel}\\gg {{L}\\bot} ) the distribution is found to scale as a Gaussian function for all tested system sizes and boundary conditions.
CURRENT STATUS OF NONPARAMETRIC STATISTICS
Directory of Open Access Journals (Sweden)
Orlov A. I.
2015-02-01
Full Text Available Nonparametric statistics is one of the five points of growth of applied mathematical statistics. Despite the large number of publications on specific issues of nonparametric statistics, the internal structure of this research direction has remained undeveloped. The purpose of this article is to consider its division into regions based on the existing practice of scientific activity determination of nonparametric statistics and classify investigations on nonparametric statistical methods. Nonparametric statistics allows to make statistical inference, in particular, to estimate the characteristics of the distribution and testing statistical hypotheses without, as a rule, weakly proven assumptions about the distribution function of samples included in a particular parametric family. For example, the widespread belief that the statistical data are often have the normal distribution. Meanwhile, analysis of results of observations, in particular, measurement errors, always leads to the same conclusion - in most cases the actual distribution significantly different from normal. Uncritical use of the hypothesis of normality often leads to significant errors, in areas such as rejection of outlying observation results (emissions, the statistical quality control, and in other cases. Therefore, it is advisable to use nonparametric methods, in which the distribution functions of the results of observations are imposed only weak requirements. It is usually assumed only their continuity. On the basis of generalization of numerous studies it can be stated that to date, using nonparametric methods can solve almost the same number of tasks that previously used parametric methods. Certain statements in the literature are incorrect that nonparametric methods have less power, or require larger sample sizes than parametric methods. Note that in the nonparametric statistics, as in mathematical statistics in general, there remain a number of unresolved problems
Energy Technology Data Exchange (ETDEWEB)
Lee, Jong Kyeom; Kim, Tae Yun; Kim, Hyun Su; Chai, Jang Bom; Lee, Jin Woo [Div. of Mechanical Engineering, Ajou University, Suwon (Korea, Republic of)
2016-10-15
This paper presents an advanced estimation method for obtaining the probability density functions of a damage parameter for valve leakage detection in a reciprocating pump. The estimation method is based on a comparison of model data which are simulated by using a mathematical model, and experimental data which are measured on the inside and outside of the reciprocating pump in operation. The mathematical model, which is simplified and extended on the basis of previous models, describes not only the normal state of the pump, but also its abnormal state caused by valve leakage. The pressure in the cylinder is expressed as a function of the crankshaft angle, and an additional volume flow rate due to the valve leakage is quantified by a damage parameter in the mathematical model. The change in the cylinder pressure profiles due to the suction valve leakage is noticeable in the compression and expansion modes of the pump. The damage parameter value over 300 cycles is calculated in two ways, considering advance or delay in the opening and closing angles of the discharge valves. The probability density functions of the damage parameter are compared for diagnosis and prognosis on the basis of the probabilistic features of valve leakage.
Nonparametric statistical methods using R
Kloke, John
2014-01-01
A Practical Guide to Implementing Nonparametric and Rank-Based ProceduresNonparametric Statistical Methods Using R covers traditional nonparametric methods and rank-based analyses, including estimation and inference for models ranging from simple location models to general linear and nonlinear models for uncorrelated and correlated responses. The authors emphasize applications and statistical computation. They illustrate the methods with many real and simulated data examples using R, including the packages Rfit and npsm.The book first gives an overview of the R language and basic statistical c
Nemeth, Noel
2013-01-01
Models that predict the failure probability of monolithic glass and ceramic components under multiaxial loading have been developed by authors such as Batdorf, Evans, and Matsuo. These "unit-sphere" failure models assume that the strength-controlling flaws are randomly oriented, noninteracting planar microcracks of specified geometry but of variable size. This report develops a formulation to describe the probability density distribution of the orientation of critical strength-controlling flaws that results from an applied load. This distribution is a function of the multiaxial stress state, the shear sensitivity of the flaws, the Weibull modulus, and the strength anisotropy. Examples are provided showing the predicted response on the unit sphere for various stress states for isotropic and transversely isotropic (anisotropic) materials--including the most probable orientation of critical flaws for offset uniaxial loads with strength anisotropy. The author anticipates that this information could be used to determine anisotropic stiffness degradation or anisotropic damage evolution for individual brittle (or quasi-brittle) composite material constituents within finite element or micromechanics-based software
Nonparametric Bayes analysis of social science data
Kunihama, Tsuyoshi
Social science data often contain complex characteristics that standard statistical methods fail to capture. Social surveys assign many questions to respondents, which often consist of mixed-scale variables. Each of the variables can follow a complex distribution outside parametric families and associations among variables may have more complicated structures than standard linear dependence. Therefore, it is not straightforward to develop a statistical model which can approximate structures well in the social science data. In addition, many social surveys have collected data over time and therefore we need to incorporate dynamic dependence into the models. Also, it is standard to observe massive number of missing values in the social science data. To address these challenging problems, this thesis develops flexible nonparametric Bayesian methods for the analysis of social science data. Chapter 1 briefly explains backgrounds and motivations of the projects in the following chapters. Chapter 2 develops a nonparametric Bayesian modeling of temporal dependence in large sparse contingency tables, relying on a probabilistic factorization of the joint pmf. Chapter 3 proposes nonparametric Bayes inference on conditional independence with conditional mutual information used as a measure of the strength of conditional dependence. Chapter 4 proposes a novel Bayesian density estimation method in social surveys with complex designs where there is a gap between sample and population. We correct for the bias by adjusting mixture weights in Bayesian mixture models. Chapter 5 develops a nonparametric model for mixed-scale longitudinal surveys, in which various types of variables can be induced through latent continuous variables and dynamic latent factors lead to flexibly time-varying associations among variables.
Learning Grasp Affordance Densities
DEFF Research Database (Denmark)
Detry, Renaud; Kraft, Dirk; Kroemer, Oliver
2011-01-01
We address the issue of learning and representing object grasp affordance models. We model grasp affordances with continuous probability density functions (grasp densities) which link object-relative grasp poses to their success probability. The underlying function representation is nonparametric...... and relies on kernel density estimation to provide a continuous model. Grasp densities are learned and refined from exploration, by letting a robot “play” with an object in a sequence of graspand-drop actions: The robot uses visual cues to generate a set of grasp hypotheses; it then executes...... these and records their outcomes. When a satisfactory number of grasp data is available, an importance-sampling algorithm turns these into a grasp density. We evaluate our method in a largely autonomous learning experiment run on three objects of distinct shapes. The experiment shows how learning increases success...
Wang, Haifeng; Popov, Pavel; Hiremath, Varun; Lantz, Steven; Viswanathan, Sharadha; Pope, Stephen
2010-11-01
A large-eddy simulation (LES)/probability density function (PDF) code is developed and applied to the study of local extinction and re-ignition in Sandia Flame E. The modified Curl mixing model is used to account for the sub-filter scalar mixing; the ARM1 mechanism is used for the chemical reaction; and the in- situ adaptive tabulation (ISAT) algorithm is used to accelerate the chemistry calculations. Calculations are performed on different grids to study the resolution requirement for this flame. Then, with sufficient grid resolution, full-scale LES/PDF calculations are performed to study the flame characteristics and the turbulence-chemistry interactions. Sensitivity to the mixing frequency model is explored in order to understand the behavior of sub-filter scalar mixing in the context of LES. The simulation results are compared to the experimental data to demonstrate the capability of the code. Comparison is also made to previous RANS/PDF simulations.
Anderson, Johan; Johansson, Jonas
2016-12-01
An analytical derivation of the probability density function (PDF) tail describing the strongly correlated interface growth governed by the nonlinear Kardar-Parisi-Zhang equation is provided. The PDF tail exactly coincides with a Tracy-Widom distribution i.e. a PDF tail proportional to \\exp ≤ft(-cw23/2\\right) , where w 2 is the the width of the interface. The PDF tail is computed by the instanton method in the strongly non-linear regime within the Martin-Siggia-Rose framework using a careful treatment of the non-linear interactions. In addition, the effect of spatial dimensions on the PDF tail scaling is discussed. This gives a novel approach to understand the rightmost PDF tail of the interface width distribution and the analysis suggests that there is no upper critical dimension.
Radożycki, Tomasz
2016-11-01
The probability density distributions for the ground states of certain model systems in quantum mechanics and for their classical counterparts are considered. It is shown, that classical distributions are remarkably improved by incorporating into them the Heisenberg uncertainty relation between position and momentum. Even the crude form of this incorporation makes the agreement between classical and quantum distributions unexpectedly good, except for the small area, where classical momenta are large. It is demonstrated that the slight improvement of this form, makes the classical distribution very similar to the quantum one in the whole space. The obtained results are much better than those from the WKB method. The paper is devoted to ground states, but the method applies to excited states too.
Dey, Santanu
2012-01-01
We consider the problem of efficient simulation estimation of the density function at the tails, and the probability of large deviations for a sum of independent, identically distributed, light-tailed and non-lattice random vectors. The latter problem besides being of independent interest, also forms a building block for more complex rare event problems that arise, for instance, in queuing and financial credit risk modeling. It has been extensively studied in literature where state independent exponential twisting based importance sampling has been shown to be asymptotically efficient and a more nuanced state dependent exponential twisting has been shown to have a stronger bounded relative error property. We exploit the saddle-point based representations that exist for these rare quantities, which rely on inverting the characteristic functions of the underlying random vectors. We note that these representations reduce the rare event estimation problem to evaluating certain integrals, which may via importance ...
Iliadis, Christian; Champagne, Art; Coc, Alain; Fitzgerald, Ryan
2010-01-01
Numerical values of charged-particle thermonuclear reaction rates for nuclei in the A=14 to 40 region are tabulated. The results are obtained using a method, based on Monte Carlo techniques, that has been described in the preceding paper of this series (Paper I). We present a low rate, median rate and high rate which correspond to the 0.16, 0.50 and 0.84 quantiles, respectively, of the cumulative reaction rate distribution. The meaning of these quantities is in general different from the commonly reported, but statistically meaningless expressions, "lower limit", "nominal value" and "upper limit" of the total reaction rate. In addition, we approximate the Monte Carlo probability density function of the total reaction rate by a lognormal distribution and tabulate the lognormal parameters {\\mu} and {\\sigma} at each temperature. We also provide a quantitative measure (Anderson-Darling test statistic) for the reliability of the lognormal approximation. The user can implement the approximate lognormal reaction rat...
Wacławczyk, M.; Grebenev, V. N.; Oberlack, M.
2017-04-01
The problem of turbulence statistics described by the Lundgren–Monin–Novikov (LMN) hierarchy of integro-differential equations is studied in terms of its group properties. For this we perform a Lie group analysis of a truncated LMN chain which presents the first two equations in an infinite set of integro-differential equations for the multi-point probability density functions (pdf’s) of velocity. A complete set of point transformations is derived for the one-point pdf’s and the independent variables: sample space of velocity, space and time. For this purpose we use a direct method based on the canonical Lie–Bäcklund operator. Due to the one-way coupling of correlation equations, the present results are complete in the sense that no additional symmetries exist for the first leading equation, even if the full infinite hierarchy is considered.
Earth Data Analysis Center, University of New Mexico — USFS, State Forestry, BLM, and DOI fire occurrence point locations from 1987 to 2008 were combined and converted into a fire occurrence probability or density grid...
Kitayabu, Toru; Hagiwara, Mao; Ishikawa, Hiroyasu; Shirai, Hiroshi
A novel delta-sigma modulator that employs a non-uniform quantizer whose spacing is adjusted by reference to the statistical properties of the input signal is proposed. The proposed delta-sigma modulator has less quantization noise compared to the one that uses a uniform quantizer with the same number of output values. With respect to the quantizer on its own, Lloyd proposed a non-uniform quantizer that is best for minimizing the average quantization noise power. The applicable condition of the method is that the statistical properties of the input signal, the probability density, are given. However, the procedure cannot be directly applied to the quantizer in the delta-sigma modulator because it jeopardizes the modulator's stability. In this paper, a procedure is proposed that determine the spacing of the quantizer with avoiding instability. Simulation results show that the proposed method reduces quantization noise by up to 3.8dB and 2.8dB with the input signal having a PAPR of 16dB and 12dB, respectively, compared to the one employing a uniform quantizer. Two alternative types of probability density function (PDF) are used in the proposed method for the calculation of the output values. One is the PDF of the input signal to the delta-sigma modulator and the other is an approximated PDF of the input signal to the quantizer inside the delta-sigma modulator. Both approaches are evaluated to find that the latter gives lower quantization noise.
Zhao, Zhijun; Liao, Rui
2011-03-01
Free-space optical (FSO) communication systems suffer from average power loss and instantaneous power fading due to the atmospheric turbulence. The channel fading probability density function (pdf) is of critical importance for FSO communication system design and evaluation. The performance and reliability of FSO communication systems can be greatly enhanced if fast-tacking devices are employed at the transmitter in order to compensate laser beam wander at the receiver aperture. The fast-tracking method is especially effective when communication distance is long. This paper studies the fading probability density functions of both fast-tracked and untracked FSO communication channels. Large-scale wave-optics simulations are conducted for both tracked and untracked lasers. In the simulations, the Kolmogorov spectrum is adopted, and it is assumed that the outer scale is infinitely large and the inner scale is negligibly small. The fading pdfs of both fast-tracked and untracked FSO channels are obtained from the simulations. Results show that the fast-tracked channel fading can be accurately modeled as gamma-distributed if receiver aperture size is smaller than the coherence radius. An analytical method is given for calculating the untracked fading pdfs of both point-like and finite-size receiver apertures from the fast-tracked fading pdf. For point-like apertures, the analytical method gives pdfs close to the well-known gamma-gamma pdfs if off-axis effects are omitted in the formulation. When off-axis effects are taken into consideration, the untracked pdfs obtained using the analytical method fit the simulation pdfs better than gamma-gamma distributions for point-like apertures, and closely fit the simulation pdfs for finite-size apertures where gamma-gamma pdfs deviate from those of the simulations significantly.
Poverty and life cycle effects: A nonparametric analysis for Germany
Stich, Andreas
1996-01-01
Most empirical studies on poverty consider the extent of poverty either for the entire society or for separate groups like elderly people.However, these papers do not show what the situation looks like for persons of a certain age. In this paper poverty measures depending on age are derived using the joint density of income and age. The density is nonparametrically estimated by weighted Gaussian kernel density estimation. Applying the conditional density of income to several poverty measures ...
Coverage Accuracy of Confidence Intervals in Nonparametric Regression
Institute of Scientific and Technical Information of China (English)
Song-xi Chen; Yong-song Qin
2003-01-01
Point-wise confidence intervals for a nonparametric regression function with random design points are considered. The confidence intervals are those based on the traditional normal approximation and the empirical likelihood. Their coverage accuracy is assessed by developing the Edgeworth expansions for the coverage probabilities. It is shown that the empirical likelihood confidence intervals are Bartlett correctable.
Storkel, Holly L; Hoover, Jill R
2011-06-01
The goal of this study was to examine the influence of part-word phonotactic probability/neighborhood density on word learning by preschool children with normal vocabularies that varied in size. Ninety-eight children (age 2 ; 11-6 ; 0) were taught consonant-vowel-consonant (CVC) nonwords orthogonally varying in the probability/density of the CV (i.e. body) and VC (i.e. rhyme). Learning was measured via picture naming. Children with the lowest expressive vocabulary scores showed no effect of either CV or VC probability/density, although floor effects could not be ruled out. In contrast, children with low or high expressive vocabulary scores demonstrated sensitivity to part-word probability/density with the nature of the effect varying by group. Children with the highest expressive vocabulary scores displayed yet a third pattern of part-word probability/density effects. Taken together, word learning by preschool children was influenced by part-word probability/density but the nature of this influence appeared to depend on the size of the lexicon.
Kim, Junmo; Fisher, John W; Yezzi, Anthony; Cetin, Müjdat; Willsky, Alan S
2005-10-01
In this paper, we present a new information-theoretic approach to image segmentation. We cast the segmentation problem as the maximization of the mutual information between the region labels and the image pixel intensities, subject to a constraint on the total length of the region boundaries. We assume that the probability densities associated with the image pixel intensities within each region are completely unknown a priori, and we formulate the problem based on nonparametric density estimates. Due to the nonparametric structure, our method does not require the image regions to have a particular type of probability distribution and does not require the extraction and use of a particular statistic. We solve the information-theoretic optimization problem by deriving the associated gradient flows and applying curve evolution techniques. We use level-set methods to implement the resulting evolution. The experimental results based on both synthetic and real images demonstrate that the proposed technique can solve a variety of challenging image segmentation problems. Futhermore, our method, which does not require any training, performs as good as methods based on training.
DPpackage: Bayesian Semi- and Nonparametric Modeling in R
Directory of Open Access Journals (Sweden)
Alejandro Jara
2011-04-01
Full Text Available Data analysis sometimes requires the relaxation of parametric assumptions in order to gain modeling flexibility and robustness against mis-specification of the probability model. In the Bayesian context, this is accomplished by placing a prior distribution on a function space, such as the space of all probability distributions or the space of all regression functions. Unfortunately, posterior distributions ranging over function spaces are highly complex and hence sampling methods play a key role. This paper provides an introduction to a simple, yet comprehensive, set of programs for the implementation of some Bayesian nonparametric and semiparametric models in R, DPpackage. Currently, DPpackage includes models for marginal and conditional density estimation, receiver operating characteristic curve analysis, interval-censored data, binary regression data, item response data, longitudinal and clustered data using generalized linear mixed models, and regression data using generalized additive models. The package also contains functions to compute pseudo-Bayes factors for model comparison and for eliciting the precision parameter of the Dirichlet process prior, and a general purpose Metropolis sampling algorithm. To maximize computational efficiency, the actual sampling for each model is carried out using compiled C, C++ or Fortran code.
Sedinger, J.S.; Chelgren, N.D.; Ward, D.H.; Lindberg, M.S.
2008-01-01
1. Patterns of temporary emigration (associated with non-breeding) are important components of variation in individual quality. Permanent emigration from the natal area has important implications for both individual fitness and local population dynamics. 2. We estimated both permanent and temporary emigration of black brent geese (Branta bernicla nigricans Lawrence) from the Tutakoke River colony, using observations of marked brent geese on breeding and wintering areas, and recoveries of ringed individuals by hunters. We used the likelihood developed by Lindberg, Kendall, Hines & Anderson 2001 (Combining band recovery data and Pollock's robust design to model temporary and permanent emigration. Biometrics, 57, 273-281) to assess hypotheses and estimate parameters. 3. Temporary emigration (the converse of breeding) varied among age classes up to age 5, and differed between individuals that bred in the previous years vs. those that did not. Consistent with the hypothesis of variation in individual quality, individuals with a higher probability of breeding in one year also had a higher probability of breeding the next year. 4. Natal fidelity of females ranged from 0.70 ?? 0.07-0.96 ?? 0.18 and averaged 0.83. In contrast to Lindberg et al. (1998), we did not detect a relationship between fidelity and local population density. Natal fidelity was negatively correlated with first-year survival, suggesting that competition among individuals of the same age for breeding territories influenced dispersal. Once females nested at the Tutakoke River, colony breeding fidelity was 1.0. 5. Our analyses show substantial variation in individual quality associated with fitness, which other analyses suggest is strongly influenced by early environment. Our analyses also suggest substantial interchange among breeding colonies of brent geese, as first shown by Lindberg et al. (1998).
Kim, Kyu Rang; Kim, Mijin; Choe, Ho-Seong; Han, Mae Ja; Lee, Hye-Rim; Oh, Jae-Won; Kim, Baek-Jo
2016-07-01
Pollen is an important cause of respiratory allergic reactions. As individual sanitation has improved, allergy risk has increased, and this trend is expected to continue due to climate change. Atmospheric pollen concentration is highly influenced by weather conditions. Regression analysis and modeling of the relationships between airborne pollen concentrations and weather conditions were performed to analyze and forecast pollen conditions. Traditionally, daily pollen concentration has been estimated using regression models that describe the relationships between observed pollen concentrations and weather conditions. These models were able to forecast daily concentrations at the sites of observation, but lacked broader spatial applicability beyond those sites. To overcome this limitation, an integrated modeling scheme was developed that is designed to represent the underlying processes of pollen production and distribution. A maximum potential for airborne pollen is first determined using the Weibull probability density function. Then, daily pollen concentration is estimated using multiple regression models. Daily risk grade levels are determined based on the risk criteria used in Korea. The mean percentages of agreement between the observed and estimated levels were 81.4-88.2 % and 92.5-98.5 % for oak and Japanese hop pollens, respectively. The new models estimated daily pollen risk more accurately than the original statistical models because of the newly integrated biological response curves. Although they overestimated seasonal mean concentration, they did not simulate all of the peak concentrations. This issue would be resolved by adding more variables that affect the prevalence and internal maturity of pollens.
Rispens, Judith; Baker, Anne; Duinmeijer, Iris
2015-02-01
The effects of neighborhood density (ND) and lexical frequency on word recognition and the effects of phonotactic probability (PP) on nonword repetition (NWR) were examined to gain insight into processing at the lexical and sublexical levels in typically developing (TD) children and children with developmental language problems. Tasks measuring NWR and word recognition were administered to 5 groups of children: 2 groups of TD children (5 and 8 years old), children with specific language impairment (SLI), children with reading impairment (RI), and children with SLI+RI (all 7-8 years old). High ND had a negative effect on word recognition in the older TD children and in the children with RI only. There was no ND effect in the younger children or in the children with SLI, who all had lower receptive vocabulary scores than the age-matched TD children and the RI groups. For all groups, NWR items with low PP were more difficult to repeat than items with high PP. This effect was especially pronounced in children with RI. Both the stage of vocabulary development and the type of language impairment (SLI or RI) impact the way ND and PP affect word recognition and NWR.
Kim, Kyu Rang; Kim, Mijin; Choe, Ho-Seong; Han, Mae Ja; Lee, Hye-Rim; Oh, Jae-Won; Kim, Baek-Jo
2017-02-01
Pollen is an important cause of respiratory allergic reactions. As individual sanitation has improved, allergy risk has increased, and this trend is expected to continue due to climate change. Atmospheric pollen concentration is highly influenced by weather conditions. Regression analysis and modeling of the relationships between airborne pollen concentrations and weather conditions were performed to analyze and forecast pollen conditions. Traditionally, daily pollen concentration has been estimated using regression models that describe the relationships between observed pollen concentrations and weather conditions. These models were able to forecast daily concentrations at the sites of observation, but lacked broader spatial applicability beyond those sites. To overcome this limitation, an integrated modeling scheme was developed that is designed to represent the underlying processes of pollen production and distribution. A maximum potential for airborne pollen is first determined using the Weibull probability density function. Then, daily pollen concentration is estimated using multiple regression models. Daily risk grade levels are determined based on the risk criteria used in Korea. The mean percentages of agreement between the observed and estimated levels were 81.4-88.2 % and 92.5-98.5 % for oak and Japanese hop pollens, respectively. The new models estimated daily pollen risk more accurately than the original statistical models because of the newly integrated biological response curves. Although they overestimated seasonal mean concentration, they did not simulate all of the peak concentrations. This issue would be resolved by adding more variables that affect the prevalence and internal maturity of pollens.
Energy Technology Data Exchange (ETDEWEB)
Kikuchi, Ryota; Misaka, Takashi; Obayashi, Shigeru, E-mail: rkikuchi@edge.ifs.tohoku.ac.jp [Institute of Fluid Science, Tohoku University, 2-1-1 Katahira, Aoba-ku, Sendai, Miyagi 980-8577 (Japan)
2015-10-15
An integrated method of a proper orthogonal decomposition based reduced-order model (ROM) and data assimilation is proposed for the real-time prediction of an unsteady flow field. In this paper, a particle filter (PF) and an ensemble Kalman filter (EnKF) are compared for data assimilation and the difference in the predicted flow fields is evaluated focusing on the probability density function (PDF) of the model variables. The proposed method is demonstrated using identical twin experiments of an unsteady flow field around a circular cylinder at the Reynolds number of 1000. The PF and EnKF are employed to estimate temporal coefficients of the ROM based on the observed velocity components in the wake of the circular cylinder. The prediction accuracy of ROM-PF is significantly better than that of ROM-EnKF due to the flexibility of PF for representing a PDF compared to EnKF. Furthermore, the proposed method reproduces the unsteady flow field several orders faster than the reference numerical simulation based on the Navier–Stokes equations. (paper)
Kikuchi, Ryota; Misaka, Takashi; Obayashi, Shigeru
2015-10-01
An integrated method of a proper orthogonal decomposition based reduced-order model (ROM) and data assimilation is proposed for the real-time prediction of an unsteady flow field. In this paper, a particle filter (PF) and an ensemble Kalman filter (EnKF) are compared for data assimilation and the difference in the predicted flow fields is evaluated focusing on the probability density function (PDF) of the model variables. The proposed method is demonstrated using identical twin experiments of an unsteady flow field around a circular cylinder at the Reynolds number of 1000. The PF and EnKF are employed to estimate temporal coefficients of the ROM based on the observed velocity components in the wake of the circular cylinder. The prediction accuracy of ROM-PF is significantly better than that of ROM-EnKF due to the flexibility of PF for representing a PDF compared to EnKF. Furthermore, the proposed method reproduces the unsteady flow field several orders faster than the reference numerical simulation based on the Navier-Stokes equations.
Nonparametric estimation of ultrasound pulses
DEFF Research Database (Denmark)
Jensen, Jørgen Arendt; Leeman, Sidney
1994-01-01
An algorithm for nonparametric estimation of 1D ultrasound pulses in echo sequences from human tissues is derived. The technique is a variation of the homomorphic filtering technique using the real cepstrum, and the underlying basis of the method is explained. The algorithm exploits a priori...
Testing discontinuities in nonparametric regression
Dai, Wenlin
2017-01-19
In nonparametric regression, it is often needed to detect whether there are jump discontinuities in the mean function. In this paper, we revisit the difference-based method in [13 H.-G. Müller and U. Stadtmüller, Discontinuous versus smooth regression, Ann. Stat. 27 (1999), pp. 299–337. doi: 10.1214/aos/1018031100
Uniform Consistency for Nonparametric Estimators in Null Recurrent Time Series
DEFF Research Database (Denmark)
Gao, Jiti; Kanaya, Shin; Li, Degui
2015-01-01
This paper establishes uniform consistency results for nonparametric kernel density and regression estimators when time series regressors concerned are nonstationary null recurrent Markov chains. Under suitable regularity conditions, we derive uniform convergence rates of the estimators. Our...... results can be viewed as a nonstationary extension of some well-known uniform consistency results for stationary time series....
Directory of Open Access Journals (Sweden)
Tatsuhiko Sato
Full Text Available We here propose a new model assembly for estimating the surviving fraction of cells irradiated with various types of ionizing radiation, considering both targeted and nontargeted effects in the same framework. The probability densities of specific energies in two scales, which are the cell nucleus and its substructure called a domain, were employed as the physical index for characterizing the radiation fields. In the model assembly, our previously established double stochastic microdosimetric kinetic (DSMK model was used to express the targeted effect, whereas a newly developed model was used to express the nontargeted effect. The radioresistance caused by overexpression of anti-apoptotic protein Bcl-2 known to frequently occur in human cancer was also considered by introducing the concept of the adaptive response in the DSMK model. The accuracy of the model assembly was examined by comparing the computationally and experimentally determined surviving fraction of Bcl-2 cells (Bcl-2 overexpressing HeLa cells and Neo cells (neomycin resistant gene-expressing HeLa cells irradiated with microbeam or broadbeam of energetic heavy ions, as well as the WI-38 normal human fibroblasts irradiated with X-ray microbeam. The model assembly reproduced very well the experimentally determined surviving fraction over a wide range of dose and linear energy transfer (LET values. Our newly established model assembly will be worth being incorporated into treatment planning systems for heavy-ion therapy, brachytherapy, and boron neutron capture therapy, given critical roles of the frequent Bcl-2 overexpression and the nontargeted effect in estimating therapeutic outcomes and harmful effects of such advanced therapeutic modalities.
Jian, Y; Yao, R; Mulnix, T; Jin, X; Carson, R E
2015-01-07
Resolution degradation in PET image reconstruction can be caused by inaccurate modeling of the physical factors in the acquisition process. Resolution modeling (RM) is a common technique that takes into account the resolution degrading factors in the system matrix. Our previous work has introduced a probability density function (PDF) method of deriving the resolution kernels from Monte Carlo simulation and parameterizing the LORs to reduce the number of kernels needed for image reconstruction. In addition, LOR-PDF allows different PDFs to be applied to LORs from different crystal layer pairs of the HRRT. In this study, a thorough test was performed with this new model (LOR-PDF) applied to two PET scanners-the HRRT and Focus-220. A more uniform resolution distribution was observed in point source reconstructions by replacing the spatially-invariant kernels with the spatially-variant LOR-PDF. Specifically, from the center to the edge of radial field of view (FOV) of the HRRT, the measured in-plane FWHMs of point sources in a warm background varied slightly from 1.7 mm to 1.9 mm in LOR-PDF reconstructions. In Minihot and contrast phantom reconstructions, LOR-PDF resulted in up to 9% higher contrast at any given noise level than image-space resolution model. LOR-PDF also has the advantage in performing crystal-layer-dependent resolution modeling. The contrast improvement by using LOR-PDF was verified statistically by replicate reconstructions. In addition, [(11)C]AFM rats imaged on the HRRT and [(11)C]PHNO rats imaged on the Focus-220 were utilized to demonstrated the advantage of the new model. Higher contrast between high-uptake regions of only a few millimeter diameter and the background was observed in LOR-PDF reconstruction than in other methods.
Sato, Tatsuhiko; Hamada, Nobuyuki
2014-01-01
We here propose a new model assembly for estimating the surviving fraction of cells irradiated with various types of ionizing radiation, considering both targeted and nontargeted effects in the same framework. The probability densities of specific energies in two scales, which are the cell nucleus and its substructure called a domain, were employed as the physical index for characterizing the radiation fields. In the model assembly, our previously established double stochastic microdosimetric kinetic (DSMK) model was used to express the targeted effect, whereas a newly developed model was used to express the nontargeted effect. The radioresistance caused by overexpression of anti-apoptotic protein Bcl-2 known to frequently occur in human cancer was also considered by introducing the concept of the adaptive response in the DSMK model. The accuracy of the model assembly was examined by comparing the computationally and experimentally determined surviving fraction of Bcl-2 cells (Bcl-2 overexpressing HeLa cells) and Neo cells (neomycin resistant gene-expressing HeLa cells) irradiated with microbeam or broadbeam of energetic heavy ions, as well as the WI-38 normal human fibroblasts irradiated with X-ray microbeam. The model assembly reproduced very well the experimentally determined surviving fraction over a wide range of dose and linear energy transfer (LET) values. Our newly established model assembly will be worth being incorporated into treatment planning systems for heavy-ion therapy, brachytherapy, and boron neutron capture therapy, given critical roles of the frequent Bcl-2 overexpression and the nontargeted effect in estimating therapeutic outcomes and harmful effects of such advanced therapeutic modalities.
Bayesian nonparametric estimation and consistency of mixed multinomial logit choice models
De Blasi, Pierpaolo; Lau, John W; 10.3150/09-BEJ233
2011-01-01
This paper develops nonparametric estimation for discrete choice models based on the mixed multinomial logit (MMNL) model. It has been shown that MMNL models encompass all discrete choice models derived under the assumption of random utility maximization, subject to the identification of an unknown distribution $G$. Noting the mixture model description of the MMNL, we employ a Bayesian nonparametric approach, using nonparametric priors on the unknown mixing distribution $G$, to estimate choice probabilities. We provide an important theoretical support for the use of the proposed methodology by investigating consistency of the posterior distribution for a general nonparametric prior on the mixing distribution. Consistency is defined according to an $L_1$-type distance on the space of choice probabilities and is achieved by extending to a regression model framework a recent approach to strong consistency based on the summability of square roots of prior probabilities. Moving to estimation, slightly different te...
Nonparametric predictive inference for combining diagnostic tests with parametric copula
Muhammad, Noryanti; Coolen, F. P. A.; Coolen-Maturi, T.
2017-09-01
Measuring the accuracy of diagnostic tests is crucial in many application areas including medicine and health care. The Receiver Operating Characteristic (ROC) curve is a popular statistical tool for describing the performance of diagnostic tests. The area under the ROC curve (AUC) is often used as a measure of the overall performance of the diagnostic test. In this paper, we interest in developing strategies for combining test results in order to increase the diagnostic accuracy. We introduce nonparametric predictive inference (NPI) for combining two diagnostic test results with considering dependence structure using parametric copula. NPI is a frequentist statistical framework for inference on a future observation based on past data observations. NPI uses lower and upper probabilities to quantify uncertainty and is based on only a few modelling assumptions. While copula is a well-known statistical concept for modelling dependence of random variables. A copula is a joint distribution function whose marginals are all uniformly distributed and it can be used to model the dependence separately from the marginal distributions. In this research, we estimate the copula density using a parametric method which is maximum likelihood estimator (MLE). We investigate the performance of this proposed method via data sets from the literature and discuss results to show how our method performs for different family of copulas. Finally, we briefly outline related challenges and opportunities for future research.
Nonparametric estimation of quantum states, processes and measurements
Lougovski, Pavel; Bennink, Ryan
Quantum state, process, and measurement estimation methods traditionally use parametric models, in which the number and role of relevant parameters is assumed to be known. When such an assumption cannot be justified, a common approach in many disciplines is to fit the experimental data to multiple models with different sets of parameters and utilize an information criterion to select the best fitting model. However, it is not always possible to assume a model with a finite (countable) number of parameters. This typically happens when there are unobserved variables that stem from hidden correlations that can only be unveiled after collecting experimental data. How does one perform quantum characterization in this situation? We present a novel nonparametric method of experimental quantum system characterization based on the Dirichlet Process (DP) that addresses this problem. Using DP as a prior in conjunction with Bayesian estimation methods allows us to increase model complexity (number of parameters) adaptively as the number of experimental observations grows. We illustrate our approach for the one-qubit case and show how a probability density function for an unknown quantum process can be estimated.
Nonparametric Inference for Periodic Sequences
Sun, Ying
2012-02-01
This article proposes a nonparametric method for estimating the period and values of a periodic sequence when the data are evenly spaced in time. The period is estimated by a "leave-out-one-cycle" version of cross-validation (CV) and complements the periodogram, a widely used tool for period estimation. The CV method is computationally simple and implicitly penalizes multiples of the smallest period, leading to a "virtually" consistent estimator of integer periods. This estimator is investigated both theoretically and by simulation.We also propose a nonparametric test of the null hypothesis that the data have constantmean against the alternative that the sequence of means is periodic. Finally, our methodology is demonstrated on three well-known time series: the sunspots and lynx trapping data, and the El Niño series of sea surface temperatures. © 2012 American Statistical Association and the American Society for Quality.
Nonparametric Econometrics: The np Package
Directory of Open Access Journals (Sweden)
Tristen Hayﬁeld
2008-07-01
Full Text Available We describe the R np package via a series of applications that may be of interest to applied econometricians. The np package implements a variety of nonparametric and semiparametric kernel-based estimators that are popular among econometricians. There are also procedures for nonparametric tests of signiﬁcance and consistent model speciﬁcation tests for parametric mean regression models and parametric quantile regression models, among others. The np package focuses on kernel methods appropriate for the mix of continuous, discrete, and categorical data often found in applied settings. Data-driven methods of bandwidth selection are emphasized throughout, though we caution the user that data-driven bandwidth selection methods can be computationally demanding.
Nonparametric estimation for hazard rate monotonously decreasing system
Institute of Scientific and Technical Information of China (English)
Han Fengyan; Li Weisong
2005-01-01
Estimation of density and hazard rate is very important to the reliability analysis of a system. In order to estimate the density and hazard rate of a hazard rate monotonously decreasing system, a new nonparametric estimator is put forward. The estimator is based on the kernel function method and optimum algorithm. Numerical experiment shows that the method is accurate enough and can be used in many cases.
Astronomical Methods for Nonparametric Regression
Steinhardt, Charles L.; Jermyn, Adam
2017-01-01
I will discuss commonly used techniques for nonparametric regression in astronomy. We find that several of them, particularly running averages and running medians, are generically biased, asymmetric between dependent and independent variables, and perform poorly in recovering the underlying function, even when errors are present only in one variable. We then examine less-commonly used techniques such as Multivariate Adaptive Regressive Splines and Boosted Trees and find them superior in bias, asymmetry, and variance both theoretically and in practice under a wide range of numerical benchmarks. In this context the chief advantage of the common techniques is runtime, which even for large datasets is now measured in microseconds compared with milliseconds for the more statistically robust techniques. This points to a tradeoff between bias, variance, and computational resources which in recent years has shifted heavily in favor of the more advanced methods, primarily driven by Moore's Law. Along these lines, we also propose a new algorithm which has better overall statistical properties than all techniques examined thus far, at the cost of significantly worse runtime, in addition to providing guidance on choosing the nonparametric regression technique most suitable to any specific problem. We then examine the more general problem of errors in both variables and provide a new algorithm which performs well in most cases and lacks the clear asymmetry of existing non-parametric methods, which fail to account for errors in both variables.
Gray, Shelley; Pittman, Andrea; Weinhold, Juliet
2014-01-01
Purpose: In this study, the authors assessed the effects of phonotactic probability and neighborhood density on word-learning configuration by preschoolers with specific language impairment (SLI) and typical language development (TD). Method: One hundred thirty-one children participated: 48 with SLI, 44 with TD matched on age and gender, and 39…
Nonparametric regression with filtered data
Linton, Oliver; Nielsen, Jens Perch; Van Keilegom, Ingrid; 10.3150/10-BEJ260
2011-01-01
We present a general principle for estimating a regression function nonparametrically, allowing for a wide variety of data filtering, for example, repeated left truncation and right censoring. Both the mean and the median regression cases are considered. The method works by first estimating the conditional hazard function or conditional survivor function and then integrating. We also investigate improved methods that take account of model structure such as independent errors and show that such methods can improve performance when the model structure is true. We establish the pointwise asymptotic normality of our estimators.
Nonparametric identification of copula structures
Li, Bo
2013-06-01
We propose a unified framework for testing a variety of assumptions commonly made about the structure of copulas, including symmetry, radial symmetry, joint symmetry, associativity and Archimedeanity, and max-stability. Our test is nonparametric and based on the asymptotic distribution of the empirical copula process.We perform simulation experiments to evaluate our test and conclude that our method is reliable and powerful for assessing common assumptions on the structure of copulas, particularly when the sample size is moderately large. We illustrate our testing approach on two datasets. © 2013 American Statistical Association.
Multiatlas segmentation as nonparametric regression.
Awate, Suyash P; Whitaker, Ross T
2014-09-01
This paper proposes a novel theoretical framework to model and analyze the statistical characteristics of a wide range of segmentation methods that incorporate a database of label maps or atlases; such methods are termed as label fusion or multiatlas segmentation. We model these multiatlas segmentation problems as nonparametric regression problems in the high-dimensional space of image patches. We analyze the nonparametric estimator's convergence behavior that characterizes expected segmentation error as a function of the size of the multiatlas database. We show that this error has an analytic form involving several parameters that are fundamental to the specific segmentation problem (determined by the chosen anatomical structure, imaging modality, registration algorithm, and label-fusion algorithm). We describe how to estimate these parameters and show that several human anatomical structures exhibit the trends modeled analytically. We use these parameter estimates to optimize the regression estimator. We show that the expected error for large database sizes is well predicted by models learned on small databases. Thus, a few expert segmentations can help predict the database sizes required to keep the expected error below a specified tolerance level. Such cost-benefit analysis is crucial for deploying clinical multiatlas segmentation systems.
A contingency table approach to nonparametric testing
Rayner, JCW
2000-01-01
Most texts on nonparametric techniques concentrate on location and linear-linear (correlation) tests, with less emphasis on dispersion effects and linear-quadratic tests. Tests for higher moment effects are virtually ignored. Using a fresh approach, A Contingency Table Approach to Nonparametric Testing unifies and extends the popular, standard tests by linking them to tests based on models for data that can be presented in contingency tables.This approach unifies popular nonparametric statistical inference and makes the traditional, most commonly performed nonparametric analyses much more comp
Nonparametric statistics for social and behavioral sciences
Kraska-MIller, M
2013-01-01
Introduction to Research in Social and Behavioral SciencesBasic Principles of ResearchPlanning for ResearchTypes of Research Designs Sampling ProceduresValidity and Reliability of Measurement InstrumentsSteps of the Research Process Introduction to Nonparametric StatisticsData AnalysisOverview of Nonparametric Statistics and Parametric Statistics Overview of Parametric Statistics Overview of Nonparametric StatisticsImportance of Nonparametric MethodsMeasurement InstrumentsAnalysis of Data to Determine Association and Agreement Pearson Chi-Square Test of Association and IndependenceContingency
Ballestra, Luca Vincenzo; Pacelli, Graziella; Radi, Davide
2016-12-01
We propose a numerical method to compute the first-passage probability density function in a time-changed Brownian model. In particular, we derive an integral representation of such a density function in which the integrand functions must be obtained solving a system of Volterra equations of the first kind. In addition, we develop an ad-hoc numerical procedure to regularize and solve this system of integral equations. The proposed method is tested on three application problems of interest in mathematical finance, namely the calculation of the survival probability of an indebted firm, the pricing of a single-knock-out put option and the pricing of a double-knock-out put option. The results obtained reveal that the novel approach is extremely accurate and fast, and performs significantly better than the finite difference method.
Hadjiagapiou, Ioannis A.
2014-03-01
The magnetic systems with disorder form an important class of systems, which are under intensive studies, since they reflect real systems. Such a class of systems is the spin glass one, which combines randomness and frustration. The Sherrington-Kirkpatrick Ising spin glass with random couplings in the presence of a random magnetic field is investigated in detail within the framework of the replica method. The two random variables (exchange integral interaction and random magnetic field) are drawn from a joint Gaussian probability density function characterized by a correlation coefficient ρ. The thermodynamic properties and phase diagrams are studied with respect to the natural parameters of both random components of the system contained in the probability density. The de Almeida-Thouless line is explored as a function of temperature, ρ and other system parameters. The entropy for zero temperature as well as for non zero temperatures is partly negative or positive, acquiring positive branches as h0 increases.
Directory of Open Access Journals (Sweden)
Abdelkader Mokkadem
2011-01-01
Full Text Available Let and denote the location and the size of the mode of a probability density. We study the joint convergence rates of semirecursive kernel estimators of and . We show how the estimation of the size of the mode allows measuring the relevance of the estimation of its location. We also enlighten that, beyond their computational advantage on nonrecursive estimators, the semirecursive estimators are preferable to use for the construction of confidence regions.
Institute of Scientific and Technical Information of China (English)
LI Jing-Hui
2008-01-01
A three-state Markovian noise is investigated. Its probability density and statistical properties are obtained. Escape of particles for a system with potential barrier only driven by this noise is investigated. It is shown that, in some circumstances, this noise can make the particles escape over the potential barrier; but in other circumstances, it cannot. Resonant activation phenomenon appears for the system considered by us.
Nonparametric Bayesian Modeling of Complex Networks
DEFF Research Database (Denmark)
Schmidt, Mikkel Nørgaard; Mørup, Morten
2013-01-01
Modeling structure in complex networks using Bayesian nonparametrics makes it possible to specify flexible model structures and infer the adequate model complexity from the observed data. This article provides a gentle introduction to nonparametric Bayesian modeling of complex networks: Using...... for complex networks can be derived and point out relevant literature....
An asymptotically optimal nonparametric adaptive controller
Institute of Scientific and Technical Information of China (English)
郭雷; 谢亮亮
2000-01-01
For discrete-time nonlinear stochastic systems with unknown nonparametric structure, a kernel estimation-based nonparametric adaptive controller is constructed based on truncated certainty equivalence principle. Global stability and asymptotic optimality of the closed-loop systems are established without resorting to any external excitations.
Probability density evolution method of fatigue strength-life relationship%疲劳强度-寿命关系的概率密度演化方法
Institute of Scientific and Technical Information of China (English)
徐亚洲; 白国良
2013-01-01
Taking degradation of fatigue strength with increase in loading cycles into account, the joint probability density evolution equation of fatigue strength and random factors was derived using Euler description. A probability density S-N (p-S-N) surface was obtained with a numerical method, it was used to calculate the p-S-N curve with a given survivability. The analysis based on experimental fatigue data indicated that p-S-N curves with 95% survivability predicted by p-S-N, Monte Carlo simulation and S-N relation ship having parameters with a given fractile agree well; p-S-N provides a complete probability description of S-N relationship, independent of a probability distribution assumption.%基于疲劳强度随加载循环次数增加不断劣化的物理事实,采用Euler描述推导出疲劳强度与随机参数联合概率密度函数满足的演化方程.采用数值求解方法,给出疲劳强度-寿命概率密度曲面(probability density S-N),并可据此计算给定存活率的P-S-N曲线.基于疲劳试验结果的算例分析表明,疲劳强度-寿命概率密度曲面、MonteCarlo模拟及具有给定分位数参数的S-N关系三者计算的p-S-N曲线吻合良好.疲劳强度-寿命概率密度演化方法可不依赖分布假定给出S-N关系的完备概率描述.
Nonparametric Detection of Geometric Structures Over Networks
Zou, Shaofeng; Liang, Yingbin; Poor, H. Vincent
2017-10-01
Nonparametric detection of existence of an anomalous structure over a network is investigated. Nodes corresponding to the anomalous structure (if one exists) receive samples generated by a distribution q, which is different from a distribution p generating samples for other nodes. If an anomalous structure does not exist, all nodes receive samples generated by p. It is assumed that the distributions p and q are arbitrary and unknown. The goal is to design statistically consistent tests with probability of errors converging to zero as the network size becomes asymptotically large. Kernel-based tests are proposed based on maximum mean discrepancy that measures the distance between mean embeddings of distributions into a reproducing kernel Hilbert space. Detection of an anomalous interval over a line network is first studied. Sufficient conditions on minimum and maximum sizes of candidate anomalous intervals are characterized in order to guarantee the proposed test to be consistent. It is also shown that certain necessary conditions must hold to guarantee any test to be universally consistent. Comparison of sufficient and necessary conditions yields that the proposed test is order-level optimal and nearly optimal respectively in terms of minimum and maximum sizes of candidate anomalous intervals. Generalization of the results to other networks is further developed. Numerical results are provided to demonstrate the performance of the proposed tests.
Institute of Scientific and Technical Information of China (English)
雷庆祝; 秦永松
2007-01-01
本文用经验似然方法讨论了条件密度的置信区间的构造.通过对覆盖概率的Edgeworth展开得到了经验似然置信区间的覆盖精度,同时证明了条件密度的经验似然置信区间的Bartlett可修正性.%Point-wise confidence intervals for a conditional probability density function are considered.The confidence intervals are based on the empirical likelihood. Their coverage accuracy is assessed by developing Edgeworth expansions for the coverage probabilities. It is shown that the empirical likelihood confidence intervals are Bartlett correctable.
Van Hooydonk, G
2011-01-01
We review harmonic oscillator theory for closed, stable quantum systems. The H2 potential energy curve (PEC) of Mexican hat-type, calculated with a confined Kratzer oscillator, is better than the Rydberg-Klein-Rees (RKR) H2 PEC. Compared with QM, the theory of chemical bonding is simplified, since a confined Kratzer oscillator gives the long sought for universal function, once called the Holy Grail of Molecular Spectroscopy. This is validated with HF, I2, N2 and O2 PECs. We quantify the entanglement of spatially separated H2 quantum states, which gives a braid view. The equal probability for H2, originating either from HA+HB or HB+HA, is quantified with a Gauss probability density function. At the Bohr scale, confined harmonic oscillators behave properly at all extremes of bound two-nucleon quantum systems and are likely to be useful also at the nuclear scale.
基于新概率密度函数的ICA盲源分离%ICA Blind Signal Separation Based on a New Probability Density Function
Institute of Scientific and Technical Information of China (English)
张娟娟; 邸双亮
2014-01-01
This paper is concerned with the blind source separation (BSS) problem of super-Gaussian and sub-Gaussian mixed signal by using the maximum likelihood method, which is based on independent component analysis (ICA) method. In this paper, we construct a new type of probability density function (PDF) which is different from the already existing PDF used to separate mixed signals in the previously published papers. Applying the new constructed PDF to estimate probability density of super-Gaussian and sub-Gaussian signals (assuming the source signals are independent of each other), it is not necessary to change the parameter values artificially, and the separation work may be performed adaptively. Numerical experiments verify the feasibility of the newly constructed PDF, and the convergence time and the separation effect are improved compared with the original algorithm.%基于独立分量分析(Independent Component Analysis, ICA)，利用极大似然估计法，研究了超高斯和亚高斯的混合信号的盲源分离(Blind Sources Separation, BSS)问题。文中构造了一种新的、不同于以往文章中用来分离混合信号的概率密度函数(Probability Density Function, PDF)。新构造的PDF无需改变函数中的参数值，可用来对于超高斯和亚高斯信号的概率密度进行估计(假设未知源信号是相互独立的)。数值实验验证了新构造的PDF的可行性，与原算法相比，收敛时间和分离效果都得到了较大的改善。
Zhao, Zhibiao
2011-06-01
We address the nonparametric model validation problem for hidden Markov models with partially observable variables and hidden states. We achieve this goal by constructing a nonparametric simultaneous confidence envelope for transition density function of the observable variables and checking whether the parametric density estimate is contained within such an envelope. Our specification test procedure is motivated by a functional connection between the transition density of the observable variables and the Markov transition kernel of the hidden states. Our approach is applicable for continuous time diffusion models, stochastic volatility models, nonlinear time series models, and models with market microstructure noise.
A method for density estimation based on expectation identities
Peralta, Joaquín; Loyola, Claudia; Loguercio, Humberto; Davis, Sergio
2017-06-01
We present a simple and direct method for non-parametric estimation of a one-dimensional probability density, based on the application of the recent conjugate variables theorem. The method expands the logarithm of the probability density ln P(x|I) in terms of a complete basis and numerically solves for the coefficients of the expansion using a linear system of equations. No Monte Carlo sampling is needed. We present preliminary results that show the practical usefulness of the method for modeling statistical data.
Parametric and Non-Parametric System Modelling
DEFF Research Database (Denmark)
Nielsen, Henrik Aalborg
1999-01-01
considered. It is shown that adaptive estimation in conditional parametric models can be performed by combining the well known methods of local polynomial regression and recursive least squares with exponential forgetting. The approach used for estimation in conditional parametric models also highlights how....... For this purpose non-parametric methods together with additive models are suggested. Also, a new approach specifically designed to detect non-linearities is introduced. Confidence intervals are constructed by use of bootstrapping. As a link between non-parametric and parametric methods a paper dealing with neural...... the focus is on combinations of parametric and non-parametric methods of regression. This combination can be in terms of additive models where e.g. one or more non-parametric term is added to a linear regression model. It can also be in terms of conditional parametric models where the coefficients...
Bayesian nonparametric duration model with censorship
Directory of Open Access Journals (Sweden)
Joseph Hakizamungu
2007-10-01
Full Text Available This paper is concerned with nonparametric i.i.d. durations models censored observations and we establish by a simple and unified approach the general structure of a bayesian nonparametric estimator for a survival function S. For Dirichlet prior distributions, we describe completely the structure of the posterior distribution of the survival function. These results are essentially supported by prior and posterior independence properties.
Bootstrap Estimation for Nonparametric Efficiency Estimates
1995-01-01
This paper develops a consistent bootstrap estimation procedure to obtain confidence intervals for nonparametric measures of productive efficiency. Although the methodology is illustrated in terms of technical efficiency measured by output distance functions, the technique can be easily extended to other consistent nonparametric frontier models. Variation in estimated efficiency scores is assumed to result from variation in empirical approximations to the true boundary of the production set. ...
A novel nonparametric confidence interval for differences of proportions for correlated binary data.
Duan, Chongyang; Cao, Yingshu; Zhou, Lizhi; Tan, Ming T; Chen, Pingyan
2016-11-16
Various confidence interval estimators have been developed for differences in proportions resulted from correlated binary data. However, the width of the mostly recommended Tango's score confidence interval tends to be wide, and the computing burden of exact methods recommended for small-sample data is intensive. The recently proposed rank-based nonparametric method by treating proportion as special areas under receiver operating characteristic provided a new way to construct the confidence interval for proportion difference on paired data, while the complex computation limits its application in practice. In this article, we develop a new nonparametric method utilizing the U-statistics approach for comparing two or more correlated areas under receiver operating characteristics. The new confidence interval has a simple analytic form with a new estimate of the degrees of freedom of n - 1. It demonstrates good coverage properties and has shorter confidence interval widths than that of Tango. This new confidence interval with the new estimate of degrees of freedom also leads to coverage probabilities that are an improvement on the rank-based nonparametric confidence interval. Comparing with the approximate exact unconditional method, the nonparametric confidence interval demonstrates good coverage properties even in small samples, and yet they are very easy to implement computationally. This nonparametric procedure is evaluated using simulation studies and illustrated with three real examples. The simplified nonparametric confidence interval is an appealing choice in practice for its ease of use and good performance. © The Author(s) 2016.
Furuya, Hiroyuki
2015-11-01
The first autochthonous case of dengue fever in Japan since 1945 was reported on August 27, 2014. Infection was transmitted by Aedes albopictus mosquitoes in Tokyo's Yoyogi Park. A total of 65 cases with no history of overseas travel and who may have been infected around the park were reported as of September 5, 2014. To quantify infection risk of the local epidemic, the reproduction number and vector density per person at the onset of the epidemic were estimated. The estimated probability distribution and the number of female mosquitoes per person (MPP) were determined from the data of the initial epidemic. The estimated distribution R(0i) for the initial epidemic was fitted to a Gamma distribution using location parameter 4.25, scale parameter 0.19, and shape parameter 7.76 with median 7.78 and IQR (7.21-8.40). The MPP was fitted to a normal distribution with mean 5.71 and standard deviation 0.53. Both estimated reproduction number and vector density per person at the onset of the epidemic were higher than previously reported values. These results indicate the potential for dengue outbreaks in places with elevated vector density per person, even in dengue non-endemic countries. To investigate the cause of this outbreak, further studies will be needed, including assessments of social, behavioral, and environmental factors that may have contributed to this epidemic by altering host and vector conditions in the park.
On ARMA Probability Density Estimation.
1981-12-01
definitions of the constants B0k=Ol ,...,q) and ak(kl,...,p) will be given which, for a given function f(.), uniquely define an approximator f pCq .) for each...satisfied. When using f pCq () for approximation purposes it is thus important to always verify whether or not this condition is met. In concluding
Wang, Shouyu; Xue, Liang; Yan, Keding
2017-07-01
Light scattering from randomly rough surfaces is of great significance in various fields such as remote sensing and target identification. As numerical methods can obtain scattering distributions without complex setups and complicated operations, they become important tools in light scattering study. However, most of them suffer from huge computing load and low operating efficiency, limiting their applications in dynamic measurements and high-speed detections. Here, to overcome these disadvantages, microfacet slope probability density function based method is presented, providing scattering information without computing ensemble average from numerous scattered fields, thus it can obtain light scattering distributions with extremely fast speed. Additionally, it can reach high-computing accuracy quantitatively certificated by mature light scattering computing algorithms. It is believed the provided approach is useful in light scattering study and offers potentiality for real-time detections.
Energy Technology Data Exchange (ETDEWEB)
Ramos, Alessandro Candido Lopes [CELG - Companhia Energetica de Goias, Goiania, GO (Brazil). Generation and Transmission. System' s Operation Center], E-mail: alessandro.clr@celg.com.br; Batista, Adalberto Jose [Universidade Federal de Goias (UFG), Goiania, GO (Brazil)], E-mail: batista@eee.ufg.br; Leborgne, Roberto Chouhy [Universidade Federal do Rio Grande do Sul (UFRS), Porto Alegre, RS (Brazil)], E-mail: rcl@ece.ufrgs.br; Emiliano, Pedro Henrique Mota, E-mail: ph@phph.com.br
2009-07-01
This article presents the impact of distributed generation in studies of voltage sags caused by faults in the electrical system. We simulated short-circuit-to-ground in 62 lines of 230, 138, 69 and 13.8 kV that are part of the electrical system of the city of Goiania, of Goias state . For each fault position was monitored the bus voltage of 380 V in an industrial consumer sensitive to such sags. Were inserted different levels of GD near the consumer. The simulations of a short circuit, with the monitoring bar 380 V, were performed again. A study using stochastic simulation Monte Carlo (SMC) was performed to obtain, at each level of GD, the probability curves and sags of the probability density and its voltage class. With these curves were obtained the average number of sags according to each class, that the consumer bar may be submitted annually. The simulations were performed using the Program Analysis of Simultaneous Faults - ANAFAS. In order to overcome the intrinsic limitations of the methods of simulation of this program and allow data entry via windows, a computational tool was developed in Java language. Data processing was done using the MATLAB software.
Why preferring parametric forecasting to nonparametric methods?
Jabot, Franck
2015-05-07
A recent series of papers by Charles T. Perretti and collaborators have shown that nonparametric forecasting methods can outperform parametric methods in noisy nonlinear systems. Such a situation can arise because of two main reasons: the instability of parametric inference procedures in chaotic systems which can lead to biased parameter estimates, and the discrepancy between the real system dynamics and the modeled one, a problem that Perretti and collaborators call "the true model myth". Should ecologists go on using the demanding parametric machinery when trying to forecast the dynamics of complex ecosystems? Or should they rely on the elegant nonparametric approach that appears so promising? It will be here argued that ecological forecasting based on parametric models presents two key comparative advantages over nonparametric approaches. First, the likelihood of parametric forecasting failure can be diagnosed thanks to simple Bayesian model checking procedures. Second, when parametric forecasting is diagnosed to be reliable, forecasting uncertainty can be estimated on virtual data generated with the fitted to data parametric model. In contrast, nonparametric techniques provide forecasts with unknown reliability. This argumentation is illustrated with the simple theta-logistic model that was previously used by Perretti and collaborators to make their point. It should convince ecologists to stick to standard parametric approaches, until methods have been developed to assess the reliability of nonparametric forecasting. Copyright © 2015 Elsevier Ltd. All rights reserved.
Nonparametric correlation models for portfolio allocation
DEFF Research Database (Denmark)
Aslanidis, Nektarios; Casas, Isabel
2013-01-01
breaks in correlations. Only when correlations are constant does the parametric DCC model deliver the best outcome. The methodologies are illustrated by evaluating two interesting portfolios. The first portfolio consists of the equity sector SPDRs and the S&P 500, while the second one contains major......This article proposes time-varying nonparametric and semiparametric estimators of the conditional cross-correlation matrix in the context of portfolio allocation. Simulations results show that the nonparametric and semiparametric models are best in DGPs with substantial variability or structural...... currencies. Results show the nonparametric model generally dominates the others when evaluating in-sample. However, the semiparametric model is best for out-of-sample analysis....
Recent Advances and Trends in Nonparametric Statistics
Akritas, MG
2003-01-01
The advent of high-speed, affordable computers in the last two decades has given a new boost to the nonparametric way of thinking. Classical nonparametric procedures, such as function smoothing, suddenly lost their abstract flavour as they became practically implementable. In addition, many previously unthinkable possibilities became mainstream; prime examples include the bootstrap and resampling methods, wavelets and nonlinear smoothers, graphical methods, data mining, bioinformatics, as well as the more recent algorithmic approaches such as bagging and boosting. This volume is a collection o
Correlated Non-Parametric Latent Feature Models
Doshi-Velez, Finale
2012-01-01
We are often interested in explaining data through a set of hidden factors or features. When the number of hidden features is unknown, the Indian Buffet Process (IBP) is a nonparametric latent feature model that does not bound the number of active features in dataset. However, the IBP assumes that all latent features are uncorrelated, making it inadequate for many realworld problems. We introduce a framework for correlated nonparametric feature models, generalising the IBP. We use this framework to generate several specific models and demonstrate applications on realworld datasets.
A Censored Nonparametric Software Reliability Model
Institute of Scientific and Technical Information of China (English)
无
2006-01-01
This paper analyses the effct of censoring on the estimation of failure rate, and presents a framework of a censored nonparametric software reliability model. The model is based on nonparametric testing of failure rate monotonically decreasing and weighted kernel failure rate estimation under the constraint of failure rate monotonically decreasing. Not only does the model have the advantages of little assumptions and weak constraints, but also the residual defects number of the software system can be estimated. The numerical experiment and real data analysis show that the model performs well with censored data.
Nonparametric correlation models for portfolio allocation
DEFF Research Database (Denmark)
Aslanidis, Nektarios; Casas, Isabel
2013-01-01
This article proposes time-varying nonparametric and semiparametric estimators of the conditional cross-correlation matrix in the context of portfolio allocation. Simulations results show that the nonparametric and semiparametric models are best in DGPs with substantial variability or structural...... breaks in correlations. Only when correlations are constant does the parametric DCC model deliver the best outcome. The methodologies are illustrated by evaluating two interesting portfolios. The first portfolio consists of the equity sector SPDRs and the S&P 500, while the second one contains major...
Directory of Open Access Journals (Sweden)
Daniel Ting
2010-04-01
Full Text Available Distributions of the backbone dihedral angles of proteins have been studied for over 40 years. While many statistical analyses have been presented, only a handful of probability densities are publicly available for use in structure validation and structure prediction methods. The available distributions differ in a number of important ways, which determine their usefulness for various purposes. These include: 1 input data size and criteria for structure inclusion (resolution, R-factor, etc.; 2 filtering of suspect conformations and outliers using B-factors or other features; 3 secondary structure of input data (e.g., whether helix and sheet are included; whether beta turns are included; 4 the method used for determining probability densities ranging from simple histograms to modern nonparametric density estimation; and 5 whether they include nearest neighbor effects on the distribution of conformations in different regions of the Ramachandran map. In this work, Ramachandran probability distributions are presented for residues in protein loops from a high-resolution data set with filtering based on calculated electron densities. Distributions for all 20 amino acids (with cis and trans proline treated separately have been determined, as well as 420 left-neighbor and 420 right-neighbor dependent distributions. The neighbor-independent and neighbor-dependent probability densities have been accurately estimated using Bayesian nonparametric statistical analysis based on the Dirichlet process. In particular, we used hierarchical Dirichlet process priors, which allow sharing of information between densities for a particular residue type and different neighbor residue types. The resulting distributions are tested in a loop modeling benchmark with the program Rosetta, and are shown to improve protein loop conformation prediction significantly. The distributions are available at http://dunbrack.fccc.edu/hdp.
Sheng, Ke; Cai, Jing; Brookeman, James; Molloy, Janelle; Christopher, John; Read, Paul
2006-09-01
Lung tumor motion trajectories measured by four-dimensional CT or dynamic MRI can be converted to a probability density function (PDF), which describes the probability of the tumor at a certain position, for PDF based treatment planning. Using this method in simulated sequential tomotherapy, we study the dose reduction of normal tissues and more important, the effect of PDF reproducibility on the accuracy of dosimetry. For these purposes, realistic PDFs were obtained from two dynamic MRI scans of a healthy volunteer within a 2 week interval. The first PDF was accumulated from a 300 s scan and the second PDF was calculated from variable scan times from 5 s (one breathing cycle) to 300 s. Optimized beam fluences based on the second PDF were delivered to the hypothetical gross target volume (GTV) of a lung phantom that moved following the first PDF The reproducibility between two PDFs varied from low (78%) to high (94.8%) when the second scan time increased from 5 s to 300 s. When a highly reproducible PDF was used in optimization, the dose coverage of GTV was maintained; phantom lung receiving 10%-20% prescription dose was reduced by 40%-50% and the mean phantom lung dose was reduced by 9.6%. However, optimization based on PDF with low reproducibility resulted in a 50% underdosed GTV. The dosimetric error increased nearly exponentially as the PDF error increased. Therefore, although the dose of the tumor surrounding tissue can be theoretically reduced by PDF based treatment planning, the reliability and applicability of this method highly depend on if a reproducible PDF exists and is measurable. By correlating the dosimetric error and PDF error together, a useful guideline for PDF data acquisition and patient qualification for PDF based planning can be derived.
Thirty years of nonparametric item response theory
Molenaar, W.
2001-01-01
Relationships between a mathematical measurement model and its real-world applications are discussed. A distinction is made between large data matrices commonly found in educational measurement and smaller matrices found in attitude and personality measurement. Nonparametric methods are evaluated fo
A Bayesian Nonparametric Approach to Test Equating
Karabatsos, George; Walker, Stephen G.
2009-01-01
A Bayesian nonparametric model is introduced for score equating. It is applicable to all major equating designs, and has advantages over previous equating models. Unlike the previous models, the Bayesian model accounts for positive dependence between distributions of scores from two tests. The Bayesian model and the previous equating models are…
How Are Teachers Teaching? A Nonparametric Approach
De Witte, Kristof; Van Klaveren, Chris
2014-01-01
This paper examines which configuration of teaching activities maximizes student performance. For this purpose a nonparametric efficiency model is formulated that accounts for (1) self-selection of students and teachers in better schools and (2) complementary teaching activities. The analysis distinguishes both individual teaching (i.e., a…
Nonparametric confidence intervals for monotone functions
Groeneboom, P.; Jongbloed, G.
2015-01-01
We study nonparametric isotonic confidence intervals for monotone functions. In [Ann. Statist. 29 (2001) 1699–1731], pointwise confidence intervals, based on likelihood ratio tests using the restricted and unrestricted MLE in the current status model, are introduced. We extend the method to the trea
Decompounding random sums: A nonparametric approach
DEFF Research Database (Denmark)
Hansen, Martin Bøgsted; Pitts, Susan M.
review a number of applications and consider the nonlinear inverse problem of inferring the cumulative distribution function of the components in the random sum. We review the existing literature on non-parametric approaches to the problem. The models amenable to the analysis are generalized considerably...
Nonparametric confidence intervals for monotone functions
Groeneboom, P.; Jongbloed, G.
2015-01-01
We study nonparametric isotonic confidence intervals for monotone functions. In [Ann. Statist. 29 (2001) 1699–1731], pointwise confidence intervals, based on likelihood ratio tests using the restricted and unrestricted MLE in the current status model, are introduced. We extend the method to the
A Nonparametric Analogy of Analysis of Covariance
Burnett, Thomas D.; Barr, Donald R.
1977-01-01
A nonparametric test of the hypothesis of no treatment effect is suggested for a situation where measures of the severity of the condition treated can be obtained and ranked both pre- and post-treatment. The test allows the pre-treatment rank to be used as a concomitant variable. (Author/JKS)
Panel data specifications in nonparametric kernel regression
DEFF Research Database (Denmark)
Czekaj, Tomasz Gerard; Henningsen, Arne
parametric panel data estimators to analyse the production technology of Polish crop farms. The results of our nonparametric kernel regressions generally differ from the estimates of the parametric models but they only slightly depend on the choice of the kernel functions. Based on economic reasoning, we...
How Are Teachers Teaching? A Nonparametric Approach
De Witte, Kristof; Van Klaveren, Chris
2014-01-01
This paper examines which configuration of teaching activities maximizes student performance. For this purpose a nonparametric efficiency model is formulated that accounts for (1) self-selection of students and teachers in better schools and (2) complementary teaching activities. The analysis distinguishes both individual teaching (i.e., a…
Using Mathematica to build Non-parametric Statistical Tables
Directory of Open Access Journals (Sweden)
Gloria Perez Sainz de Rozas
2003-01-01
Full Text Available In this paper, I present computational procedures to obtian statistical tables. The tables of the asymptotic distribution and the exact distribution of Kolmogorov-Smirnov statistic Dn for one population, the table of the distribution of the runs R, the table of the distribution of Wilcoxon signed-rank statistic W+ and the table of the distribution of Mann-Whitney statistic Ux using Mathematica, Version 3.9 under Window98. I think that it is an interesting cuestion because many statistical packages give the asymptotic significance level in the statistical tests and with these porcedures one can easily calculate the exact significance levels and the left-tail and right-tail probabilities with non-parametric distributions. I have used mathematica to make these calculations because one can use symbolic language to solve recursion relations. It's very easy to generate the format of the tables, and it's possible to obtain any table of the mentioned non-parametric distributions with any precision, not only with the standard parameters more used in Statistics, and without transcription mistakes. Furthermore, using similar procedures, we can generate tables for the following distribution functions: Binomial, Poisson, Hypergeometric, Normal, x2 Chi-Square, T-Student, F-Snedecor, Geometric, Gamma and Beta.
Chowdhury, Snehaunshu
2017-01-23
In this study, we demonstrate the use of a scanning mobility particle sizer (SMPS) as an effective tool to measure the probability density functions (PDFs) of soot nanoparticles in turbulent flames. Time-averaged soot PDFs necessary for validating existing soot models are reported at intervals of ∆x/D∆x/D = 5 along the centerline of turbulent, non-premixed, C2H4/N2 flames. The jet exit Reynolds numbers of the flames investigated were 10,000 and 20,000. A simplified burner geometry based on a published design was chosen to aid modelers. Soot was sampled directly from the flame using a sampling probe with a 0.5-mm diameter orifice and diluted with N2 by a two-stage dilution process. The overall dilution ratio was not evaluated. An SMPS system was used to analyze soot particle concentrations in the diluted samples. Sampling conditions were optimized over a wide range of dilution ratios to eliminate the effect of agglomeration in the sampling probe. Two differential mobility analyzers (DMAs) with different size ranges were used separately in the SMPS measurements to characterize the entire size range of particles. In both flames, the PDFs were found to be mono-modal in nature near the jet exit. Further downstream, the profiles were flatter with a fall-off at larger particle diameters. The geometric mean of the soot size distributions was less than 10 nm for all cases and increased monotonically with axial distance in both flames.
Vargas-Melendez, Leandro; Boada, Beatriz L; Boada, Maria Jesus L; Gauchia, Antonio; Diaz, Vicente
2017-04-29
Vehicles with a high center of gravity (COG), such as light trucks and heavy vehicles, are prone to rollover. This kind of accident causes nearly 33 % of all deaths from passenger vehicle crashes. Nowadays, these vehicles are incorporating roll stability control (RSC) systems to improve their safety. Most of the RSC systems require the vehicle roll angle as a known input variable to predict the lateral load transfer. The vehicle roll angle can be directly measured by a dual antenna global positioning system (GPS), but it is expensive. For this reason, it is important to estimate the vehicle roll angle from sensors installed onboard in current vehicles. On the other hand, the knowledge of the vehicle's parameters values is essential to obtain an accurate vehicle response. Some of vehicle parameters cannot be easily obtained and they can vary over time. In this paper, an algorithm for the simultaneous on-line estimation of vehicle's roll angle and parameters is proposed. This algorithm uses a probability density function (PDF)-based truncation method in combination with a dual Kalman filter (DKF), to guarantee that both vehicle's states and parameters are within bounds that have a physical meaning, using the information obtained from sensors mounted on vehicles. Experimental results show the effectiveness of the proposed algorithm.
Institute of Scientific and Technical Information of China (English)
SantiagoLain; RicardoAliod
2000-01-01
A statistical formalism overcoming some conceptual and practical difficulties arising in existing two-phase flow (2PHF) mathematical modelling has been applied to propose a model for dilute 2PHF turbulent flows.Phase interaction terms with a clear physical meaning enter the equations and the formalism provides some guidelines for the avoidance of closure assumptions or the rational approximation of these terms. Continuous phase averaged continuity, momentum, turbulent kinetic energy and turbulence dissipation rate equations have been rigorously and systematically obtained in a single step. These equations display a structure similar to that for single-phase flows.It is also assumed that dispersed phase dynamics is well described by a probability density function (pdf) equation and Eulerian continuity, momentum and fluctuating kinetic energy equations for the dispersed phase are deduced.An extension of the standard k-c turbulence model for the continuous phase is used. A gradient transport model is adopted for the dispersed phase fluctuating fluxes of momentum and kinetic energy at the non-colliding, large inertia limit. This model is then used to predict the behaviour of three axisymmetric turbulent jets of air laden with solid particles varying in size and concentration. Qualitative and quantitative numerical predictions compare reasonably well with the three different sets of experimental results, studying the influence of particle size, loading ratio and flow confinement velocity.
Livingston, Richard A.; Jin, Shuang
2005-05-01
Bridges and other civil structures can exhibit nonlinear and/or chaotic behavior under ambient traffic or wind loadings. The probability density function (pdf) of the observed structural responses thus plays an important role for long-term structural health monitoring, LRFR and fatigue life analysis. However, the actual pdf of such structural response data often has a very complicated shape due to its fractal nature. Various conventional methods to approximate it can often lead to biased estimates. This paper presents recent research progress at the Turner-Fairbank Highway Research Center of the FHWA in applying a novel probabilistic scaling scheme for enhanced maximum entropy evaluation to find the most unbiased pdf. The maximum entropy method is applied with a fractal interpolation formulation based on contraction mappings through an iterated function system (IFS). Based on a fractal dimension determined from the entire response data set by an algorithm involving the information dimension, a characteristic uncertainty parameter, called the probabilistic scaling factor, can be introduced. This allows significantly enhanced maximum entropy evaluation through the added inferences about the fine scale fluctuations in the response data. Case studies using the dynamic response data sets collected from a real world bridge (Commodore Barry Bridge, PA) and from the simulation of a classical nonlinear chaotic system (the Lorenz system) are presented in this paper. The results illustrate the advantages of the probabilistic scaling method over conventional approaches for finding the unbiased pdf especially in the critical tail region that contains the larger structural responses.
Directory of Open Access Journals (Sweden)
Jun Zhang
2013-12-01
Full Text Available Divergence functions are the non-symmetric “distance” on the manifold, Μθ, of parametric probability density functions over a measure space, (Χ,μ. Classical information geometry prescribes, on Μθ: (i a Riemannian metric given by the Fisher information; (ii a pair of dual connections (giving rise to the family of α-connections that preserve the metric under parallel transport by their joint actions; and (iii a family of divergence functions ( α-divergence defined on Μθ x Μθ, which induce the metric and the dual connections. Here, we construct an extension of this differential geometric structure from Μθ (that of parametric probability density functions to the manifold, Μ, of non-parametric functions on X, removing the positivity and normalization constraints. The generalized Fisher information and α-connections on M are induced by an α-parameterized family of divergence functions, reflecting the fundamental convex inequality associated with any smooth and strictly convex function. The infinite-dimensional manifold, M, has zero curvature for all these α-connections; hence, the generally non-zero curvature of M can be interpreted as arising from an embedding of Μθ into Μ. Furthermore, when a parametric model (after a monotonic scaling forms an affine submanifold, its natural and expectation parameters form biorthogonal coordinates, and such a submanifold is dually flat for α = ± 1, generalizing the results of Amari’s α-embedding. The present analysis illuminates two different types of duality in information geometry, one concerning the referential status of a point (measurable function expressed in the divergence function (“referential duality” and the other concerning its representation under an arbitrary monotone scaling (“representational duality”.
Probability in quantum mechanics
Directory of Open Access Journals (Sweden)
J. G. Gilson
1982-01-01
Full Text Available By using a fluid theory which is an alternative to quantum theory but from which the latter can be deduced exactly, the long-standing problem of how quantum mechanics is related to stochastic processes is studied. It can be seen how the Schrödinger probability density has a relationship to time spent on small sections of an orbit, just as the probability density has in some classical contexts.
Kh., S Rezaei; Hanson, R J; Fouesneau, M
2016-01-01
We present a non-parametric model for inferring the three-dimensional (3D) distribution of dust density in the Milky Way. Our approach uses the extinction measured towards stars at different locations in the Galaxy at approximately known distances. Each extinction measurement is proportional to the integrated dust density along its line-of-sight. Making simple assumptions about the spatial correlation of the dust density, we can infer the most probable 3D distribution of dust across the entire observed region, including along sight lines which were not observed. This is possible because our model employs a Gaussian Process to connect all lines-of-sight. We demonstrate the capability of our model to capture detailed dust density variations using mock data as well as simulated data from the Gaia Universe Model Snapshot. We then apply our method to a sample of giant stars observed by APOGEE and Kepler to construct a 3D dust map over a small region of the Galaxy. Due to our smoothness constraint and its isotropy,...
Non-parametric seismic hazard analysis in the presence of incomplete data
Yazdani, Azad; Mirzaei, Sajjad; Dadkhah, Koroush
2017-01-01
The distribution of earthquake magnitudes plays a crucial role in the estimation of seismic hazard parameters. Due to the complexity of earthquake magnitude distribution, non-parametric approaches are recommended over classical parametric methods. The main deficiency of the non-parametric approach is the lack of complete magnitude data in almost all cases. This study aims to introduce an imputation procedure for completing earthquake catalog data that will allow the catalog to be used for non-parametric density estimation. Using a Monte Carlo simulation, the efficiency of introduced approach is investigated. This study indicates that when a magnitude catalog is incomplete, the imputation procedure can provide an appropriate tool for seismic hazard assessment. As an illustration, the imputation procedure was applied to estimate earthquake magnitude distribution in Tehran, the capital city of Iran.
Nonparametric forecasting of low-dimensional dynamical systems.
Berry, Tyrus; Giannakis, Dimitrios; Harlim, John
2015-03-01
This paper presents a nonparametric modeling approach for forecasting stochastic dynamical systems on low-dimensional manifolds. The key idea is to represent the discrete shift maps on a smooth basis which can be obtained by the diffusion maps algorithm. In the limit of large data, this approach converges to a Galerkin projection of the semigroup solution to the underlying dynamics on a basis adapted to the invariant measure. This approach allows one to quantify uncertainties (in fact, evolve the probability distribution) for nontrivial dynamical systems with equation-free modeling. We verify our approach on various examples, ranging from an inhomogeneous anisotropic stochastic differential equation on a torus, the chaotic Lorenz three-dimensional model, and the Niño-3.4 data set which is used as a proxy of the El Niño Southern Oscillation.
Bayesian Bandwidth Selection for a Nonparametric Regression Model with Mixed Types of Regressors
Directory of Open Access Journals (Sweden)
Xibin Zhang
2016-04-01
Full Text Available This paper develops a sampling algorithm for bandwidth estimation in a nonparametric regression model with continuous and discrete regressors under an unknown error density. The error density is approximated by the kernel density estimator of the unobserved errors, while the regression function is estimated using the Nadaraya-Watson estimator admitting continuous and discrete regressors. We derive an approximate likelihood and posterior for bandwidth parameters, followed by a sampling algorithm. Simulation results show that the proposed approach typically leads to better accuracy of the resulting estimates than cross-validation, particularly for smaller sample sizes. This bandwidth estimation approach is applied to nonparametric regression model of the Australian All Ordinaries returns and the kernel density estimation of gross domestic product (GDP growth rates among the organisation for economic co-operation and development (OECD and non-OECD countries.
Chang, Ju Yong
2016-08-01
We present a new gesture recognition method that is based on the conditional random field (CRF) model using multiple feature matching. Our approach solves the labeling problem, determining gesture categories and their temporal ranges at the same time. A generative probabilistic model is formalized and probability densities are nonparametrically estimated by matching input features with a training dataset. In addition to the conventional skeletal joint-based features, the appearance information near the active hand in an RGB image is exploited to capture the detailed motion of fingers. The estimated likelihood function is then used as the unary term for our CRF model. The smoothness term is also incorporated to enforce the temporal coherence of our solution. Frame-wise recognition results can then be obtained by applying an efficient dynamic programming technique. To estimate the parameters of the proposed CRF model, we incorporate the structured support vector machine (SSVM) framework that can perform efficient structured learning by using large-scale datasets. Experimental results demonstrate that our method provides effective gesture recognition results for challenging real gesture datasets. By scoring 0.8563 in the mean Jaccard index, our method has obtained the state-of-the-art results for the gesture recognition track of the 2014 ChaLearn Looking at People (LAP) Challenge.
Fault prediction of fighter based on nonparametric density estimation
Institute of Scientific and Technical Information of China (English)
Zhang Zhengdao; Hu Shousong
2005-01-01
Fighters and other complex engineering systems have many characteristics such as difficult modeling and testing, multiple working situations, and high cost. Aim at these points, a new kind of real-time fault predictor is designed based on an improved k-nearest neighbor method, which needs neither the math model of system nor the training data and prior knowledge. It can study and predict while system's running, so that it can overcome the difficulty of data acquirement. Besides, this predictor has a fast prediction speed, and the false alarm rate and missing alarm rate can be adjusted randomly. The method is simple and universalizable. The result of simulation on fighter F-16 proved the efficiency.
Log-concave Probability Distributions: Theory and Statistical Testing
DEFF Research Database (Denmark)
An, Mark Yuing
1996-01-01
This paper studies the broad class of log-concave probability distributions that arise in economics of uncertainty and information. For univariate, continuous, and log-concave random variables we prove useful properties without imposing the differentiability of density functions. Discrete...... and multivariate distributions are also discussed. We propose simple non-parametric testing procedures for log-concavity. The test statistics are constructed to test one of the two implicati ons of log-concavity: increasing hazard rates and new-is-better-than-used (NBU) property. The test for increasing hazard...... rates are based on normalized spacing of the sample order statistics. The tests for NBU property fall into the category of Hoeffding's U-statistics...
Nonparametric tests for pathwise properties of semimartingales
Cont, Rama; 10.3150/10-BEJ293
2011-01-01
We propose two nonparametric tests for investigating the pathwise properties of a signal modeled as the sum of a L\\'{e}vy process and a Brownian semimartingale. Using a nonparametric threshold estimator for the continuous component of the quadratic variation, we design a test for the presence of a continuous martingale component in the process and a test for establishing whether the jumps have finite or infinite variation, based on observations on a discrete-time grid. We evaluate the performance of our tests using simulations of various stochastic models and use the tests to investigate the fine structure of the DM/USD exchange rate fluctuations and SPX futures prices. In both cases, our tests reveal the presence of a non-zero Brownian component and a finite variation jump component.
A Bayesian nonparametric meta-analysis model.
Karabatsos, George; Talbott, Elizabeth; Walker, Stephen G
2015-03-01
In a meta-analysis, it is important to specify a model that adequately describes the effect-size distribution of the underlying population of studies. The conventional normal fixed-effect and normal random-effects models assume a normal effect-size population distribution, conditionally on parameters and covariates. For estimating the mean overall effect size, such models may be adequate, but for prediction, they surely are not if the effect-size distribution exhibits non-normal behavior. To address this issue, we propose a Bayesian nonparametric meta-analysis model, which can describe a wider range of effect-size distributions, including unimodal symmetric distributions, as well as skewed and more multimodal distributions. We demonstrate our model through the analysis of real meta-analytic data arising from behavioral-genetic research. We compare the predictive performance of the Bayesian nonparametric model against various conventional and more modern normal fixed-effects and random-effects models.
Bayesian nonparametric estimation for Quantum Homodyne Tomography
Naulet, Zacharie; Barat, Eric
2016-01-01
We estimate the quantum state of a light beam from results of quantum homodyne tomography noisy measurements performed on identically prepared quantum systems. We propose two Bayesian nonparametric approaches. The first approach is based on mixture models and is illustrated through simulation examples. The second approach is based on random basis expansions. We study the theoretical performance of the second approach by quantifying the rate of contraction of the posterior distribution around ...
portfolio optimization based on nonparametric estimation methods
Directory of Open Access Journals (Sweden)
mahsa ghandehari
2017-03-01
Full Text Available One of the major issues investors are facing with in capital markets is decision making about select an appropriate stock exchange for investing and selecting an optimal portfolio. This process is done through the risk and expected return assessment. On the other hand in portfolio selection problem if the assets expected returns are normally distributed, variance and standard deviation are used as a risk measure. But, the expected returns on assets are not necessarily normal and sometimes have dramatic differences from normal distribution. This paper with the introduction of conditional value at risk ( CVaR, as a measure of risk in a nonparametric framework, for a given expected return, offers the optimal portfolio and this method is compared with the linear programming method. The data used in this study consists of monthly returns of 15 companies selected from the top 50 companies in Tehran Stock Exchange during the winter of 1392 which is considered from April of 1388 to June of 1393. The results of this study show the superiority of nonparametric method over the linear programming method and the nonparametric method is much faster than the linear programming method.
Introduction to nonparametric statistics for the biological sciences using R
MacFarland, Thomas W
2016-01-01
This book contains a rich set of tools for nonparametric analyses, and the purpose of this supplemental text is to provide guidance to students and professional researchers on how R is used for nonparametric data analysis in the biological sciences: To introduce when nonparametric approaches to data analysis are appropriate To introduce the leading nonparametric tests commonly used in biostatistics and how R is used to generate appropriate statistics for each test To introduce common figures typically associated with nonparametric data analysis and how R is used to generate appropriate figures in support of each data set The book focuses on how R is used to distinguish between data that could be classified as nonparametric as opposed to data that could be classified as parametric, with both approaches to data classification covered extensively. Following an introductory lesson on nonparametric statistics for the biological sciences, the book is organized into eight self-contained lessons on various analyses a...
Estimating Probabilities in Recommendation Systems
Sun, Mingxuan; Kidwell, Paul
2010-01-01
Recommendation systems are emerging as an important business application with significant economic impact. Currently popular systems include Amazon's book recommendations, Netflix's movie recommendations, and Pandora's music recommendations. In this paper we address the problem of estimating probabilities associated with recommendation system data using non-parametric kernel smoothing. In our estimation we interpret missing items as randomly censored observations and obtain efficient computation schemes using combinatorial properties of generating functions. We demonstrate our approach with several case studies involving real world movie recommendation data. The results are comparable with state-of-the-art techniques while also providing probabilistic preference estimates outside the scope of traditional recommender systems.
Gudder, Stanley P
2014-01-01
Quantum probability is a subtle blend of quantum mechanics and classical probability theory. Its important ideas can be traced to the pioneering work of Richard Feynman in his path integral formalism.Only recently have the concept and ideas of quantum probability been presented in a rigorous axiomatic framework, and this book provides a coherent and comprehensive exposition of this approach. It gives a unified treatment of operational statistics, generalized measure theory and the path integral formalism that can only be found in scattered research articles.The first two chapters survey the ne
DEFF Research Database (Denmark)
Asmussen, Søren; Albrecher, Hansjörg
The book gives a comprehensive treatment of the classical and modern ruin probability theory. Some of the topics are Lundberg's inequality, the Cramér-Lundberg approximation, exact solutions, other approximations (e.g., for heavy-tailed claim size distributions), finite horizon ruin probabilities......, extensions of the classical compound Poisson model to allow for reserve-dependent premiums, Markov-modulation, periodicity, change of measure techniques, phase-type distributions as a computational vehicle and the connection to other applied probability areas, like queueing theory. In this substantially...
Burton, Robin R.
2010-04-01
Three-dimensional (3D) Light Detection And Ranging (LIDAR) systems designed for foliage penetration can produce good bare-earth products in medium to medium-heavy obscuration environments, but product creation becomes increasingly more difficult as the obscuration level increases. A prior knowledge of the obscuration environment over large areas is hard to obtain. The competing factors of area coverage rate and product quality are difficult to balance. Ground-based estimates of obscuration levels are labor intensive and only capture a small portion of the area of interest. Estimates of obscuration levels derived from airborne data require that the area of interest has been collected previously. Recently, there has been a focus on lacunarity (scale dependent measure of translational invariance) to quantify the gap structure of canopies. While this approach is useful, it needs to be evaluated relative to the size of the instantaneous field-of-view (IFOV) of the system under consideration. In this paper, the author reports on initial results to generate not just average obscuration values from overhead canopy photographs, but to generate obscuration probability density functions (PDFs) for both gimbaled linear-mode and geiger-mode airborne LIDAR. In general, gimbaled linear-mode (LM) LIDAR collects data with higher signal-to-noise (SNR), but is limited to smaller areas and cannot collect at higher altitudes. Conversely, geiger-mode (GM) LIDAR has a much lower SNR, but is capable of higher area rates and collecting data at higher altitudes. To date, geiger-mode LIDAR obscurant penetration theory has relied on a single obscuration value, but recent work has extended it to use PDFs1. Whether or not the inclusion of PDFs significantly changes predicted results and more closely matches actual results awaits the generation of PDFs over specific ground truth targets and comparison to actual collections of those ground truth targets. Ideally, examination of individual PDFs
Shiryaev, Albert N
2016-01-01
This book contains a systematic treatment of probability from the ground up, starting with intuitive ideas and gradually developing more sophisticated subjects, such as random walks, martingales, Markov chains, the measure-theoretic foundations of probability theory, weak convergence of probability measures, and the central limit theorem. Many examples are discussed in detail, and there are a large number of exercises. The book is accessible to advanced undergraduates and can be used as a text for independent study. To accommodate the greatly expanded material in the third edition of Probability, the book is now divided into two volumes. This first volume contains updated references and substantial revisions of the first three chapters of the second edition. In particular, new material has been added on generating functions, the inclusion-exclusion principle, theorems on monotonic classes (relying on a detailed treatment of “π-λ” systems), and the fundamental theorems of mathematical statistics.
Comparison of reliability techniques of parametric and non-parametric method
Directory of Open Access Journals (Sweden)
C. Kalaiselvan
2016-06-01
Full Text Available Reliability of a product or system is the probability that the product performs adequately its intended function for the stated period of time under stated operating conditions. It is function of time. The most widely used nano ceramic capacitor C0G and X7R is used in this reliability study to generate the Time-to failure (TTF data. The time to failure data are identified by Accelerated Life Test (ALT and Highly Accelerated Life Testing (HALT. The test is conducted at high stress level to generate more failure rate within the short interval of time. The reliability method used to convert accelerated to actual condition is Parametric method and Non-Parametric method. In this paper, comparative study has been done for Parametric and Non-Parametric methods to identify the failure data. The Weibull distribution is identified for parametric method; Kaplan–Meier and Simple Actuarial Method are identified for non-parametric method. The time taken to identify the mean time to failure (MTTF in accelerating condition is the same for parametric and non-parametric method with relative deviation.
Institute of Scientific and Technical Information of China (English)
何耀耀; 许启发; 杨善林; 余本功
2013-01-01
According to the problem of short-term load forecasting in the power system, this paper proposed a probability density forecasting method using radical basis function (RBF) neural network quantile regression based on the existed researches on combination forecasting and probability interval prediction. The probability density function of load at any period in a day was evaluated. The proposed method can obtain more useful information than point prediction and interval prediction, and can implement the whole probability distribution forecasting for future load. The practical data of a city in China show that the proposed probability density forecasting method can gain more accurate result of point prediction and obtain the forecasting results of integrated probability density function of short-term load.%针对电力系统短期负荷预测问题,在现有的组合预测和概率性区间预测的基础上,提出了基于RBF神经网络分位数回归的概率密度预测方法,得出未来一天中任意时期负荷的概率密度函数,可以得到比点预测和区间预测更多的有用信息,实现了对未来负荷完整概率分布的预测.中国某市实际数据的预测结果表明,提出的概率密度预测方法不仅能得出较为精确的点预测结果,而且能够获得短期负荷完整的概率密度函数预测结果.
Quantiles, parametric-select density estimation, and bi-information parameter estimators
Parzen, E.
1982-01-01
A quantile-based approach to statistical analysis and probability modeling of data is presented which formulates statistical inference problems as functional inference problems in which the parameters to be estimated are density functions. Density estimators can be non-parametric (computed independently of model identified) or parametric-select (approximated by finite parametric models that can provide standard models whose fit can be tested). Exponential models and autoregressive models are approximating densities which can be justified as maximum entropy for respectively the entropy of a probability density and the entropy of a quantile density. Applications of these ideas are outlined to the problems of modeling: (1) univariate data; (2) bivariate data and tests for independence; and (3) two samples and likelihood ratios. It is proposed that bi-information estimation of a density function can be developed by analogy to the problem of identification of regression models.
Lexicographic Probability, Conditional Probability, and Nonstandard Probability
2009-11-11
the following conditions: CP1. µ(U |U) = 1 if U ∈ F ′. CP2 . µ(V1 ∪ V2 |U) = µ(V1 |U) + µ(V2 |U) if V1 ∩ V2 = ∅, U ∈ F ′, and V1, V2 ∈ F . CP3. µ(V |U...µ(V |X)× µ(X |U) if V ⊆ X ⊆ U , U,X ∈ F ′, V ∈ F . Note that it follows from CP1 and CP2 that µ(· |U) is a probability measure on (W,F) (and, in... CP2 hold. This is easily seen to determine µ. Moreover, µ vaciously satisfies CP3, since there do not exist distinct sets U and X in F ′ such that U
A nonparametric and diversified portfolio model
Shirazi, Yasaman Izadparast; Sabiruzzaman, Md.; Hamzah, Nor Aishah
2014-07-01
Traditional portfolio models, like mean-variance (MV) suffer from estimation error and lack of diversity. Alternatives, like mean-entropy (ME) or mean-variance-entropy (MVE) portfolio models focus independently on the issue of either a proper risk measure or the diversity. In this paper, we propose an asset allocation model that compromise between risk of historical data and future uncertainty. In the new model, entropy is presented as a nonparametric risk measure as well as an index of diversity. Our empirical evaluation with a variety of performance measures shows that this model has better out-of-sample performances and lower portfolio turnover than its competitors.
Non-Parametric Estimation of Correlation Functions
DEFF Research Database (Denmark)
Brincker, Rune; Rytter, Anders; Krenk, Steen
In this paper three methods of non-parametric correlation function estimation are reviewed and evaluated: the direct method, estimation by the Fast Fourier Transform and finally estimation by the Random Decrement technique. The basic ideas of the techniques are reviewed, sources of bias are pointed...... out, and methods to prevent bias are presented. The techniques are evaluated by comparing their speed and accuracy on the simple case of estimating auto-correlation functions for the response of a single degree-of-freedom system loaded with white noise....
Lottery spending: a non-parametric analysis.
Garibaldi, Skip; Frisoli, Kayla; Ke, Li; Lim, Melody
2015-01-01
We analyze the spending of individuals in the United States on lottery tickets in an average month, as reported in surveys. We view these surveys as sampling from an unknown distribution, and we use non-parametric methods to compare properties of this distribution for various demographic groups, as well as claims that some properties of this distribution are constant across surveys. We find that the observed higher spending by Hispanic lottery players can be attributed to differences in education levels, and we dispute previous claims that the top 10% of lottery players consistently account for 50% of lottery sales.
Lottery spending: a non-parametric analysis.
Directory of Open Access Journals (Sweden)
Skip Garibaldi
Full Text Available We analyze the spending of individuals in the United States on lottery tickets in an average month, as reported in surveys. We view these surveys as sampling from an unknown distribution, and we use non-parametric methods to compare properties of this distribution for various demographic groups, as well as claims that some properties of this distribution are constant across surveys. We find that the observed higher spending by Hispanic lottery players can be attributed to differences in education levels, and we dispute previous claims that the top 10% of lottery players consistently account for 50% of lottery sales.
Nonparametric inferences for kurtosis and conditional kurtosis
Institute of Scientific and Technical Information of China (English)
XIE Xiao-heng; HE You-hua
2009-01-01
Under the assumption of strictly stationary process, this paper proposes a nonparametric model to test the kurtosis and conditional kurtosis for risk time series. We apply this method to the daily returns of S&P500 index and the Shanghai Composite Index, and simulate GARCH data for verifying the efficiency of the presented model. Our results indicate that the risk series distribution is heavily tailed, but the historical information can make its future distribution light-tailed. However the far future distribution's tails are little affected by the historical data.
Parametric versus non-parametric simulation
Dupeux, Bérénice; Buysse, Jeroen
2014-01-01
Most of ex-ante impact assessment policy models have been based on a parametric approach. We develop a novel non-parametric approach, called Inverse DEA. We use non parametric efficiency analysis for determining the farm’s technology and behaviour. Then, we compare the parametric approach and the Inverse DEA models to a known data generating process. We use a bio-economic model as a data generating process reflecting a real world situation where often non-linear relationships exist. Results s...
Preliminary results on nonparametric facial occlusion detection
Directory of Open Access Journals (Sweden)
Daniel LÓPEZ SÁNCHEZ
2016-10-01
Full Text Available The problem of face recognition has been extensively studied in the available literature, however, some aspects of this field require further research. The design and implementation of face recognition systems that can efficiently handle unconstrained conditions (e.g. pose variations, illumination, partial occlusion... is still an area under active research. This work focuses on the design of a new nonparametric occlusion detection technique. In addition, we present some preliminary results that indicate that the proposed technique might be useful to face recognition systems, allowing them to dynamically discard occluded face parts.
Directory of Open Access Journals (Sweden)
Donald W. Zimmerman
2004-01-01
Full Text Available It is well known that the two-sample Student t test fails to maintain its significance level when the variances of treatment groups are unequal, and, at the same time, sample sizes are unequal. However, introductory textbooks in psychology and education often maintain that the test is robust to variance heterogeneity when sample sizes are equal. The present study discloses that, for a wide variety of non-normal distributions, especially skewed distributions, the Type I error probabilities of both the t test and the Wilcoxon-Mann-Whitney test are substantially inflated by heterogeneous variances, even when sample sizes are equal. The Type I error rate of the t test performed on ranks replacing the scores (rank-transformed data is inflated in the same way and always corresponds closely to that of the Wilcoxon-Mann-Whitney test. For many probability densities, the distortion of the significance level is far greater after transformation to ranks and, contrary to known asymptotic properties, the magnitude of the inflation is an increasing function of sample size. Although nonparametric tests of location also can be sensitive to differences in the shape of distributions apart from location, the Wilcoxon-Mann-Whitney test and rank-transformation tests apparently are influenced mainly by skewness that is accompanied by specious differences in the means of ranks.
DEFF Research Database (Denmark)
Rojas-Nandayapa, Leonardo
Tail probabilities of sums of heavy-tailed random variables are of a major importance in various branches of Applied Probability, such as Risk Theory, Queueing Theory, Financial Management, and are subject to intense research nowadays. To understand their relevance one just needs to think...... of insurance companies facing losses due to natural disasters, banks seeking protection against huge losses, failures in expensive and sophisticated systems or loss of valuable information in electronic systems. The main difficulty when dealing with this kind of problems is the unavailability of a closed...
S Varadhan, S R
2001-01-01
This volume presents topics in probability theory covered during a first-year graduate course given at the Courant Institute of Mathematical Sciences. The necessary background material in measure theory is developed, including the standard topics, such as extension theorem, construction of measures, integration, product spaces, Radon-Nikodym theorem, and conditional expectation. In the first part of the book, characteristic functions are introduced, followed by the study of weak convergence of probability distributions. Then both the weak and strong limit theorems for sums of independent rando
Approximation of conditional densities by smooth mixtures of regressions
Norets, Andriy
2010-01-01
This paper shows that large nonparametric classes of conditional multivariate densities can be approximated in the Kullback--Leibler distance by different specifications of finite mixtures of normal regressions in which normal means and variances and mixing probabilities can depend on variables in the conditioning set (covariates). These models are a special case of models known as "mixtures of experts" in statistics and computer science literature. Flexible specifications include models in which only mixing probabilities, modeled by multinomial logit, depend on the covariates and, in the univariate case, models in which only means of the mixed normals depend flexibly on the covariates. Modeling the variance of the mixed normals by flexible functions of the covariates can weaken restrictions on the class of the approximable densities. Obtained results can be generalized to mixtures of general location scale densities. Rates of convergence and easy to interpret bounds are also obtained for different model spec...
Regularized Regression and Density Estimation based on Optimal Transport
Burger, M.
2012-03-11
The aim of this paper is to investigate a novel nonparametric approach for estimating and smoothing density functions as well as probability densities from discrete samples based on a variational regularization method with the Wasserstein metric as a data fidelity. The approach allows a unified treatment of discrete and continuous probability measures and is hence attractive for various tasks. In particular, the variational model for special regularization functionals yields a natural method for estimating densities and for preserving edges in the case of total variation regularization. In order to compute solutions of the variational problems, a regularized optimal transport problem needs to be solved, for which we discuss several formulations and provide a detailed analysis. Moreover, we compute special self-similar solutions for standard regularization functionals and we discuss several computational approaches and results. © 2012 The Author(s).
Application of Kernel Density Estimation in Lamb Wave-Based Damage Detection
Directory of Open Access Journals (Sweden)
Long Yu
2012-01-01
Full Text Available The present work concerns the estimation of the probability density function (p.d.f. of measured data in the Lamb wave-based damage detection. Although there was a number of research work which focused on the consensus algorithm of combining all the results of individual sensors, the p.d.f. of measured data, which was the fundamental part of the probability-based method, was still given by experience in existing work. Based on the analysis about the noise-induced errors in measured data, it was learned that the type of distribution was related with the level of noise. In the case of weak noise, the p.d.f. of measured data could be considered as the normal distribution. The empirical methods could give satisfied estimating results. However, in the case of strong noise, the p.d.f. was complex and did not belong to any type of common distribution function. Nonparametric methods, therefore, were needed. As the most popular nonparametric method, kernel density estimation was introduced. In order to demonstrate the performance of the kernel density estimation methods, a numerical model was built to generate the signals of Lamb waves. Three levels of white Gaussian noise were intentionally added into the simulated signals. The estimation results showed that the nonparametric methods outperformed the empirical methods in terms of accuracy.
Bayesian Nonparametric Clustering for Positive Definite Matrices.
Cherian, Anoop; Morellas, Vassilios; Papanikolopoulos, Nikolaos
2016-05-01
Symmetric Positive Definite (SPD) matrices emerge as data descriptors in several applications of computer vision such as object tracking, texture recognition, and diffusion tensor imaging. Clustering these data matrices forms an integral part of these applications, for which soft-clustering algorithms (K-Means, expectation maximization, etc.) are generally used. As is well-known, these algorithms need the number of clusters to be specified, which is difficult when the dataset scales. To address this issue, we resort to the classical nonparametric Bayesian framework by modeling the data as a mixture model using the Dirichlet process (DP) prior. Since these matrices do not conform to the Euclidean geometry, rather belongs to a curved Riemannian manifold,existing DP models cannot be directly applied. Thus, in this paper, we propose a novel DP mixture model framework for SPD matrices. Using the log-determinant divergence as the underlying dissimilarity measure to compare these matrices, and further using the connection between this measure and the Wishart distribution, we derive a novel DPM model based on the Wishart-Inverse-Wishart conjugate pair. We apply this model to several applications in computer vision. Our experiments demonstrate that our model is scalable to the dataset size and at the same time achieves superior accuracy compared to several state-of-the-art parametric and nonparametric clustering algorithms.
Comparison of three nonparametric kriging methods for delineating heavy-metal contaminated soils
Energy Technology Data Exchange (ETDEWEB)
Juang, K.W.; Lee, D.Y
2000-02-01
The probability of pollutant concentrations greater than a cutoff value is useful for delineating hazardous areas in contaminated soils. It is essential for risk assessment and reclamation. In this study, three nonparametric kriging methods [indicator kriging, probability kriging, and kriging with the cumulative distribution function (CDF) of order statistics (CDF kriging)] were used to estimate the probability of heavy-metal concentrations lower than a cutoff value. In terms of methodology, the probability kriging estimator and CDF kriging estimator take into account the information of the order relation, which is not considered in indicator kriging. Since probability kriging has been shown to be better than indicator kriging for delineating contaminated soils, the performance of CDF kriging, which the authors propose, was compared with that of probability kriging in this study. A data set of soil Cd and Pb concentrations obtained from a 10-ha heavy-metal contaminated site in Taoyuan, Taiwan, was used. The results demonstrated that the probability kriging and CDF kriging estimations were more accurate than the indicator kriging estimation. On the other hand, because the probability kriging was based on the cokriging estimator, some unreliable estimates occurred in the probability kriging estimation. This indicated that probability kriging was not as robust as CDF kriging. Therefore, CDF kriging is more suitable than probability kriging for estimating the probability of heavy-metal concentrations lower than a cutoff value.
Martins, T. M.; Alberto, J.
2015-12-01
The uncertainties of wind and solar generation patterns tends to be a critical factor in operation and expansion planning studies of electrical energy systems, as these generations are highly dependent on atmospheric variables which are difficult to predict. Traditionally, the uncertainty of renewable generation has been represented through scenarios generated by autoregressive parametric models (ARMA, PAR(p), SARIMA, etc.), that have been widely used for simulating the uncertainty of inflows and electrical demand. These methods have 3 disadvantages: (i) it is assumed that the random variables can be modelled through a known probability distribution, usually Weibull, log-normal, or normal, which are not always adequate; (ii) the temporal and spatial coupling of the represented variables are generally constructed from the Pearson Correlation, strictly requiring the hypothesis of data normality, that in the case of wind and solar generation is not met; (iii) there is an exponential increase in the model complexity due to its dimensionality. This work proposes the use of a stochastic model built from the combination of a non-parametric approach of a probability density function (the kernel density estimation method) with a dynamic Bayesian network framework. The kernel density estimation method is used to obtain the probability density function of the random variables directly from historical records, eliminating the need of choosing prior distributions. The Bayesian network allows the representation of nonlinearities in the temporal coupling of the time series, since they allow reproducing a compact probability distribution of a variable, subject to preceding stages. The proposed model was used to the generate wind power scenarios in long-term operation studies of the Brazilian Electric System, in which inflows of major rivers were also represented. The results show a considerable quality gain when compared to scenarios generated by traditional approaches.
On Wasserstein Two-Sample Testing and Related Families of Nonparametric Tests
Directory of Open Access Journals (Sweden)
Aaditya Ramdas
2017-01-01
Full Text Available Nonparametric two-sample or homogeneity testing is a decision theoretic problem that involves identifying differences between two random variables without making parametric assumptions about their underlying distributions. The literature is old and rich, with a wide variety of statistics having being designed and analyzed, both for the unidimensional and the multivariate setting. Inthisshortsurvey,wefocusonteststatisticsthatinvolvetheWassersteindistance. Usingan entropic smoothing of the Wasserstein distance, we connect these to very different tests including multivariate methods involving energy statistics and kernel based maximum mean discrepancy and univariate methods like the Kolmogorov–Smirnov test, probability or quantile (PP/QQ plots and receiver operating characteristic or ordinal dominance (ROC/ODC curves. Some observations are implicit in the literature, while others seem to have not been noticed thus far. Given nonparametric two-sample testing’s classical and continued importance, we aim to provide useful connections for theorists and practitioners familiar with one subset of methods but not others.
Directory of Open Access Journals (Sweden)
Farnoosh Basaligheh
2015-12-01
Full Text Available One of the conventional methods for temporary support of tunnels is to use steel sets with shotcrete. The nature of a temporary support system demands a quick installation of its structures. As a result, the spacing between steel sets is not a fixed amount and it can be considered as a random variable. Hence, in the reliability analysis of these types of structures, the selection of an appropriate probability distribution function of spacing of steel sets is essential. In the present paper, the distances between steel sets are collected from an under-construction tunnel and the collected data is used to suggest a proper Probability Distribution Function (PDF for the spacing of steel sets. The tunnel has two different excavation sections. In this regard, different distribution functions were investigated and three common tests of goodness of fit were used for evaluation of each function for each excavation section. Results from all three methods indicate that the Wakeby distribution function can be suggested as the proper PDF for spacing between the steel sets. It is also noted that, although the probability distribution function for two different tunnel sections is the same, the parameters of PDF for the individual sections are different from each other.
Nonparametric dark energy reconstruction from supernova data.
Holsclaw, Tracy; Alam, Ujjaini; Sansó, Bruno; Lee, Herbert; Heitmann, Katrin; Habib, Salman; Higdon, David
2010-12-10
Understanding the origin of the accelerated expansion of the Universe poses one of the greatest challenges in physics today. Lacking a compelling fundamental theory to test, observational efforts are targeted at a better characterization of the underlying cause. If a new form of mass-energy, dark energy, is driving the acceleration, the redshift evolution of the equation of state parameter w(z) will hold essential clues as to its origin. To best exploit data from observations it is necessary to develop a robust and accurate reconstruction approach, with controlled errors, for w(z). We introduce a new, nonparametric method for solving the associated statistical inverse problem based on Gaussian process modeling and Markov chain Monte Carlo sampling. Applying this method to recent supernova measurements, we reconstruct the continuous history of w out to redshift z=1.5.
Nonparametric estimation of location and scale parameters
Potgieter, C.J.
2012-12-01
Two random variables X and Y belong to the same location-scale family if there are constants μ and σ such that Y and μ+σX have the same distribution. In this paper we consider non-parametric estimation of the parameters μ and σ under minimal assumptions regarding the form of the distribution functions of X and Y. We discuss an approach to the estimation problem that is based on asymptotic likelihood considerations. Our results enable us to provide a methodology that can be implemented easily and which yields estimators that are often near optimal when compared to fully parametric methods. We evaluate the performance of the estimators in a series of Monte Carlo simulations. © 2012 Elsevier B.V. All rights reserved.
Nonparametric Maximum Entropy Estimation on Information Diagrams
Martin, Elliot A; Meinke, Alexander; Děchtěrenko, Filip; Davidsen, Jörn
2016-01-01
Maximum entropy estimation is of broad interest for inferring properties of systems across many different disciplines. In this work, we significantly extend a technique we previously introduced for estimating the maximum entropy of a set of random discrete variables when conditioning on bivariate mutual informations and univariate entropies. Specifically, we show how to apply the concept to continuous random variables and vastly expand the types of information-theoretic quantities one can condition on. This allows us to establish a number of significant advantages of our approach over existing ones. Not only does our method perform favorably in the undersampled regime, where existing methods fail, but it also can be dramatically less computationally expensive as the cardinality of the variables increases. In addition, we propose a nonparametric formulation of connected informations and give an illustrative example showing how this agrees with the existing parametric formulation in cases of interest. We furthe...
Nonparametric estimation of employee stock options
Institute of Scientific and Technical Information of China (English)
FU Qiang; LIU Li-an; LIU Qian
2006-01-01
We proposed a new model to price employee stock options (ESOs). The model is based on nonparametric statistical methods with market data. It incorporates the kernel estimator and employs a three-step method to modify BlackScholes formula. The model overcomes the limits of Black-Scholes formula in handling option prices with varied volatility. It disposes the effects of ESOs self-characteristics such as non-tradability, the longer term for expiration, the early exercise feature, the restriction on shorting selling and the employee's risk aversion on risk neutral pricing condition, and can be applied to ESOs valuation with the explanatory variable in no matter the certainty case or random case.
On Parametric (and Non-Parametric Variation
Directory of Open Access Journals (Sweden)
Neil Smith
2009-11-01
Full Text Available This article raises the issue of the correct characterization of ‘Parametric Variation’ in syntax and phonology. After specifying their theoretical commitments, the authors outline the relevant parts of the Principles–and–Parameters framework, and draw a three-way distinction among Universal Principles, Parameters, and Accidents. The core of the contribution then consists of an attempt to provide identity criteria for parametric, as opposed to non-parametric, variation. Parametric choices must be antecedently known, and it is suggested that they must also satisfy seven individually necessary and jointly sufficient criteria. These are that they be cognitively represented, systematic, dependent on the input, deterministic, discrete, mutually exclusive, and irreversible.
Nonparametric inference of network structure and dynamics
Peixoto, Tiago P.
The network structure of complex systems determine their function and serve as evidence for the evolutionary mechanisms that lie behind them. Despite considerable effort in recent years, it remains an open challenge to formulate general descriptions of the large-scale structure of network systems, and how to reliably extract such information from data. Although many approaches have been proposed, few methods attempt to gauge the statistical significance of the uncovered structures, and hence the majority cannot reliably separate actual structure from stochastic fluctuations. Due to the sheer size and high-dimensionality of many networks, this represents a major limitation that prevents meaningful interpretations of the results obtained with such nonstatistical methods. In this talk, I will show how these issues can be tackled in a principled and efficient fashion by formulating appropriate generative models of network structure that can have their parameters inferred from data. By employing a Bayesian description of such models, the inference can be performed in a nonparametric fashion, that does not require any a priori knowledge or ad hoc assumptions about the data. I will show how this approach can be used to perform model comparison, and how hierarchical models yield the most appropriate trade-off between model complexity and quality of fit based on the statistical evidence present in the data. I will also show how this general approach can be elegantly extended to networks with edge attributes, that are embedded in latent spaces, and that change in time. The latter is obtained via a fully dynamic generative network model, based on arbitrary-order Markov chains, that can also be inferred in a nonparametric fashion. Throughout the talk I will illustrate the application of the methods with many empirical networks such as the internet at the autonomous systems level, the global airport network, the network of actors and films, social networks, citations among
A nonparametric dynamic additive regression model for longitudinal data
DEFF Research Database (Denmark)
Martinussen, Torben; Scheike, Thomas H.
2000-01-01
dynamic linear models, estimating equations, least squares, longitudinal data, nonparametric methods, partly conditional mean models, time-varying-coefficient models......dynamic linear models, estimating equations, least squares, longitudinal data, nonparametric methods, partly conditional mean models, time-varying-coefficient models...
The Utility of Nonparametric Transformations for Imputation of Survey Data
Directory of Open Access Journals (Sweden)
Robbins Michael W.
2014-12-01
Full Text Available Missing values present a prevalent problem in the analysis of establishment survey data. Multivariate imputation algorithms (which are used to fill in missing observations tend to have the common limitation that imputations for continuous variables are sampled from Gaussian distributions. This limitation is addressed here through the use of robust marginal transformations. Specifically, kernel-density and empirical distribution-type transformations are discussed and are shown to have favorable properties when used for imputation of complex survey data. Although such techniques have wide applicability (i.e., they may be easily applied in conjunction with a wide array of imputation techniques, the proposed methodology is applied here with an algorithm for imputation in the USDA’s Agricultural Resource Management Survey. Data analysis and simulation results are used to illustrate the specific advantages of the robust methods when compared to the fully parametric techniques and to other relevant techniques such as predictive mean matching. To summarize, transformations based upon parametric densities are shown to distort several data characteristics in circumstances where the parametric model is ill fit; however, no circumstances are found in which the transformations based upon parametric models outperform the nonparametric transformations. As a result, the transformation based upon the empirical distribution (which is the most computationally efficient is recommended over the other transformation procedures in practice.
Tveito, Aslak; Lines, Glenn T; Edwards, Andrew G; McCulloch, Andrew
2016-07-01
Markov models are ubiquitously used to represent the function of single ion channels. However, solving the inverse problem to construct a Markov model of single channel dynamics from bilayer or patch-clamp recordings remains challenging, particularly for channels involving complex gating processes. Methods for solving the inverse problem are generally based on data from voltage clamp measurements. Here, we describe an alternative approach to this problem based on measurements of voltage traces. The voltage traces define probability density functions of the functional states of an ion channel. These probability density functions can also be computed by solving a deterministic system of partial differential equations. The inversion is based on tuning the rates of the Markov models used in the deterministic system of partial differential equations such that the solution mimics the properties of the probability density function gathered from (pseudo) experimental data as well as possible. The optimization is done by defining a cost function to measure the difference between the deterministic solution and the solution based on experimental data. By evoking the properties of this function, it is possible to infer whether the rates of the Markov model are identifiable by our method. We present applications to Markov model well-known from the literature.
Asymptotic theory of nonparametric regression estimates with censored data
Institute of Scientific and Technical Information of China (English)
施沛德; 王海燕; 张利华
2000-01-01
For regression analysis, some useful Information may have been lost when the responses are right censored. To estimate nonparametric functions, several estimates based on censored data have been proposed and their consistency and convergence rates have been studied in literat黵e, but the optimal rates of global convergence have not been obtained yet. Because of the possible Information loss, one may think that it is impossible for an estimate based on censored data to achieve the optimal rates of global convergence for nonparametric regression, which were established by Stone based on complete data. This paper constructs a regression spline estimate of a general nonparametric regression f unction based on right-censored response data, and proves, under some regularity condi-tions, that this estimate achieves the optimal rates of global convergence for nonparametric regression. Since the parameters for the nonparametric regression estimate have to be chosen based on a data driven criterion, we also obtai
Directory of Open Access Journals (Sweden)
Thomas S Churcher
2017-01-01
Full Text Available Over a century since Ronald Ross discovered that malaria is caused by the bite of an infectious mosquito it is still unclear how the number of parasites injected influences disease transmission. Currently it is assumed that all mosquitoes with salivary gland sporozoites are equally infectious irrespective of the number of parasites they harbour, though this has never been rigorously tested. Here we analyse >1000 experimental infections of humans and mice and demonstrate a dose-dependency for probability of infection and the length of the host pre-patent period. Mosquitoes with a higher numbers of sporozoites in their salivary glands following blood-feeding are more likely to have caused infection (and have done so quicker than mosquitoes with fewer parasites. A similar dose response for the probability of infection was seen for humans given a pre-erythrocytic vaccine candidate targeting circumsporozoite protein (CSP, and in mice with and without transfusion of anti-CSP antibodies. These interventions prevented infection more efficiently from bites made by mosquitoes with fewer parasites. The importance of parasite number has widespread implications across malariology, ranging from our basic understanding of the parasite, how vaccines are evaluated and the way in which transmission should be measured in the field. It also provides direct evidence for why the only registered malaria vaccine RTS,S was partially effective in recent clinical trials.
Sinden, Robert E.; Poulton, Ian D.; Griffin, Jamie T.; Upton, Leanna M.; Sala, Katarzyna A.; Angrisano, Fiona; Hill, Adrian V. S.; Blagborough, Andrew M.
2017-01-01
Over a century since Ronald Ross discovered that malaria is caused by the bite of an infectious mosquito it is still unclear how the number of parasites injected influences disease transmission. Currently it is assumed that all mosquitoes with salivary gland sporozoites are equally infectious irrespective of the number of parasites they harbour, though this has never been rigorously tested. Here we analyse >1000 experimental infections of humans and mice and demonstrate a dose-dependency for probability of infection and the length of the host pre-patent period. Mosquitoes with a higher numbers of sporozoites in their salivary glands following blood-feeding are more likely to have caused infection (and have done so quicker) than mosquitoes with fewer parasites. A similar dose response for the probability of infection was seen for humans given a pre-erythrocytic vaccine candidate targeting circumsporozoite protein (CSP), and in mice with and without transfusion of anti-CSP antibodies. These interventions prevented infection more efficiently from bites made by mosquitoes with fewer parasites. The importance of parasite number has widespread implications across malariology, ranging from our basic understanding of the parasite, how vaccines are evaluated and the way in which transmission should be measured in the field. It also provides direct evidence for why the only registered malaria vaccine RTS,S was partially effective in recent clinical trials. PMID:28081253
Institute of Scientific and Technical Information of China (English)
王浩雅; 马金晶; 王理珉; 张群芳; 孙力; 张涛; 石凤学; 和智君
2013-01-01
利用色差仪对云南9个烟区K326烤烟品种,3个部位的烟叶进行了颜色指标的测定.应用CIE 1976(L*a*b*)色空间理论,采用非参数密度估计函数,对颜色数据做非参数密度估计图,并以颜色的3个指标L、a*b*,分别作三维空间的坐标轴Z轴、X轴、Y轴,绘制了三维山峰图和等值线图.结果表明,通过三维图能够清晰地表征出3个部位的空间层次分布,通过山峰图能有空间立体层次地表现颜色指标,通过等值线图能看出每个部位颜色数据的分布情况,解决了颜色3个指标来表征一个特性的情况,可为今后颜色指标的数据库建立提供一定的基础.%In 9 tobacco - planting areas of Yunnan province, the color indicators of 3 parts of flue - cured tobacco variety K326 were measured by color difference instrument. CIE 1976(L* a* b* ) color space theory and nonparametric density estimate function were used to make nonparametric density estimation diagram of color data. Three indicators of color L, a * , b * were separately taken as the Z, X, Y coordinate axis of the three - dimensional space, and the three - dimensional peak image and contour map were drawn. The results showed that the three - dimensional peak image could clearly characterize the spatial and stepwise distributions of the three parts and color indicators. Contour map could understand the distributive conditions of color data every part, which solved a problem that three color indicators could only express a character. Therefore, it can provide a certain basis for establishing color indicator database in the future.
A Bayesian nonparametric approach to reconstruction and prediction of random dynamical systems
Merkatas, Christos; Kaloudis, Konstantinos; Hatjispyros, Spyridon J.
2017-06-01
We propose a Bayesian nonparametric mixture model for the reconstruction and prediction from observed time series data, of discretized stochastic dynamical systems, based on Markov Chain Monte Carlo methods. Our results can be used by researchers in physical modeling interested in a fast and accurate estimation of low dimensional stochastic models when the size of the observed time series is small and the noise process (perhaps) is non-Gaussian. The inference procedure is demonstrated specifically in the case of polynomial maps of an arbitrary degree and when a Geometric Stick Breaking mixture process prior over the space of densities, is applied to the additive errors. Our method is parsimonious compared to Bayesian nonparametric techniques based on Dirichlet process mixtures, flexible and general. Simulations based on synthetic time series are presented.
Estimating the joint survival probabilities of married individuals
Sanders, Lisanne; Melenberg, Bertrand
2016-01-01
We estimate the joint survival probability of spouses using a large random sample drawn from a Dutch census. As benchmarks we use two bivariate Weibull models. We consider more flexible models, using a semi-nonparametric approach, by extending the independent Weibull distribution using squared polyn
Bayesian Nonparametric Estimation for Dynamic Treatment Regimes with Sequential Transition Times.
Xu, Yanxun; Müller, Peter; Wahed, Abdus S; Thall, Peter F
2016-01-01
We analyze a dataset arising from a clinical trial involving multi-stage chemotherapy regimes for acute leukemia. The trial design was a 2 × 2 factorial for frontline therapies only. Motivated by the idea that subsequent salvage treatments affect survival time, we model therapy as a dynamic treatment regime (DTR), that is, an alternating sequence of adaptive treatments or other actions and transition times between disease states. These sequences may vary substantially between patients, depending on how the regime plays out. To evaluate the regimes, mean overall survival time is expressed as a weighted average of the means of all possible sums of successive transitions times. We assume a Bayesian nonparametric survival regression model for each transition time, with a dependent Dirichlet process prior and Gaussian process base measure (DDP-GP). Posterior simulation is implemented by Markov chain Monte Carlo (MCMC) sampling. We provide general guidelines for constructing a prior using empirical Bayes methods. The proposed approach is compared with inverse probability of treatment weighting, including a doubly robust augmented version of this approach, for both single-stage and multi-stage regimes with treatment assignment depending on baseline covariates. The simulations show that the proposed nonparametric Bayesian approach can substantially improve inference compared to existing methods. An R program for implementing the DDP-GP-based Bayesian nonparametric analysis is freely available at https://www.ma.utexas.edu/users/yxu/.
Nonparametric methods in actigraphy: An update
Directory of Open Access Journals (Sweden)
Bruno S.B. Gonçalves
2014-09-01
Full Text Available Circadian rhythmicity in humans has been well studied using actigraphy, a method of measuring gross motor movement. As actigraphic technology continues to evolve, it is important for data analysis to keep pace with new variables and features. Our objective is to study the behavior of two variables, interdaily stability and intradaily variability, to describe rest activity rhythm. Simulated data and actigraphy data of humans, rats, and marmosets were used in this study. We modified the method of calculation for IV and IS by modifying the time intervals of analysis. For each variable, we calculated the average value (IVm and ISm results for each time interval. Simulated data showed that (1 synchronization analysis depends on sample size, and (2 fragmentation is independent of the amplitude of the generated noise. We were able to obtain a significant difference in the fragmentation patterns of stroke patients using an IVm variable, while the variable IV60 was not identified. Rhythmic synchronization of activity and rest was significantly higher in young than adults with Parkinson׳s when using the ISM variable; however, this difference was not seen using IS60. We propose an updated format to calculate rhythmic fragmentation, including two additional optional variables. These alternative methods of nonparametric analysis aim to more precisely detect sleep–wake cycle fragmentation and synchronization.
Bayesian nonparametric adaptive control using Gaussian processes.
Chowdhary, Girish; Kingravi, Hassan A; How, Jonathan P; Vela, Patricio A
2015-03-01
Most current model reference adaptive control (MRAC) methods rely on parametric adaptive elements, in which the number of parameters of the adaptive element are fixed a priori, often through expert judgment. An example of such an adaptive element is radial basis function networks (RBFNs), with RBF centers preallocated based on the expected operating domain. If the system operates outside of the expected operating domain, this adaptive element can become noneffective in capturing and canceling the uncertainty, thus rendering the adaptive controller only semiglobal in nature. This paper investigates a Gaussian process-based Bayesian MRAC architecture (GP-MRAC), which leverages the power and flexibility of GP Bayesian nonparametric models of uncertainty. The GP-MRAC does not require the centers to be preallocated, can inherently handle measurement noise, and enables MRAC to handle a broader set of uncertainties, including those that are defined as distributions over functions. We use stochastic stability arguments to show that GP-MRAC guarantees good closed-loop performance with no prior domain knowledge of the uncertainty. Online implementable GP inference methods are compared in numerical simulations against RBFN-MRAC with preallocated centers and are shown to provide better tracking and improved long-term learning.
Nonparametric methods in actigraphy: An update
Gonçalves, Bruno S.B.; Cavalcanti, Paula R.A.; Tavares, Gracilene R.; Campos, Tania F.; Araujo, John F.
2014-01-01
Circadian rhythmicity in humans has been well studied using actigraphy, a method of measuring gross motor movement. As actigraphic technology continues to evolve, it is important for data analysis to keep pace with new variables and features. Our objective is to study the behavior of two variables, interdaily stability and intradaily variability, to describe rest activity rhythm. Simulated data and actigraphy data of humans, rats, and marmosets were used in this study. We modified the method of calculation for IV and IS by modifying the time intervals of analysis. For each variable, we calculated the average value (IVm and ISm) results for each time interval. Simulated data showed that (1) synchronization analysis depends on sample size, and (2) fragmentation is independent of the amplitude of the generated noise. We were able to obtain a significant difference in the fragmentation patterns of stroke patients using an IVm variable, while the variable IV60 was not identified. Rhythmic synchronization of activity and rest was significantly higher in young than adults with Parkinson׳s when using the ISM variable; however, this difference was not seen using IS60. We propose an updated format to calculate rhythmic fragmentation, including two additional optional variables. These alternative methods of nonparametric analysis aim to more precisely detect sleep–wake cycle fragmentation and synchronization. PMID:26483921
Indian Academy of Sciences (India)
Joshua Olusegun Okeniyi; Idemudia Joshua Ambrose; Stanley Okechukwu Okpala; Oluwafemi Michael Omoniyi; Isaac Oluwaseun Oladele; Cleophas Akintoye Loto; Patricia Abimbola Idowu Popoola
2014-06-01
In this study, corrosion test-data of steel-rebar in concrete were subjected to the fittings of the Normal, Gumbel and the Weibull probability distribution functions. This was done to investigate the suitability of the results of the fitted test-data, by these distributions, for modelling the effectiveness of C6H15NO3, triethanolamine (TEA), admixtures on the corrosion of steel-rebar in concrete in NaCl and in H2SO4 test-media. For this, six different concentrations of TEA were admixed in replicates of steel-reinforced concrete samples which were immersed in the saline/marine and the microbial/industrial simulating test-environments for seventy-five days. From these, distribution fittings of the non-destructive electrochemical measurements were subjected to the Kolmogorov–Smirnov goodness-of-fit statistics and to the analyses of variance modelling for studying test-data compatibility to the fittings and testing significance. Although all fittings of test-data followed similar trends of significant testing, the fittings of the corrosion rate test data followed the Weibull more than the Normal and the Gumbel distribution fittings, thus supporting use of the Weibull fittings for modelling effectiveness. The effectiveness models on rebar corrosion, based on these, identified 0.083% TEA with optimal inhibition efficiency, $\\eta =$ 72.17 ± 10.68%, in NaCl medium while 0.667% TEA was the only admixture with positive effectiveness, $\\eta =$ 56.45±15.85%, in H2SO4 medium. These results bear implications on the concentrations of TEA for effective corrosion protection of concrete steel-rebar in saline/marine and in industrial/microbial environments.
Collision Probability Analysis
DEFF Research Database (Denmark)
Hansen, Peter Friis; Pedersen, Preben Terndrup
1998-01-01
It is the purpose of this report to apply a rational model for prediction of ship-ship collision probabilities as function of the ship and the crew characteristics and the navigational environment for MS Dextra sailing on a route between Cadiz and the Canary Islands.The most important ship and crew...... characteristics are: ship speed, ship manoeuvrability, the layout of the navigational bridge, the radar system, the number and the training of navigators, the presence of a look out etc. The main parameters affecting the navigational environment are ship traffic density, probability distributions of wind speeds...... probability, i.e. a study of the navigator's role in resolving critical situations, a causation factor is derived as a second step.The report documents the first step in a probabilistic collision damage analysis. Future work will inlcude calculation of energy released for crushing of structures giving...
Nonparametric Bayesian drift estimation for multidimensional stochastic differential equations
Gugushvili, S.; Spreij, P.
2014-01-01
We consider nonparametric Bayesian estimation of the drift coefficient of a multidimensional stochastic differential equation from discrete-time observations on the solution of this equation. Under suitable regularity conditions, we establish posterior consistency in this context.
Homothetic Efficiency and Test Power: A Non-Parametric Approach
J. Heufer (Jan); P. Hjertstrand (Per)
2015-01-01
markdownabstract__Abstract__ We provide a nonparametric revealed preference approach to demand analysis based on homothetic efficiency. Homotheticity is a useful restriction but data rarely satisfies testable conditions. To overcome this we provide a way to estimate homothetic efficiency of
A non-parametric approach to investigating fish population dynamics
National Research Council Canada - National Science Library
Cook, R.M; Fryer, R.J
2001-01-01
.... Using a non-parametric model for the stock-recruitment relationship it is possible to avoid defining specific functions relating recruitment to stock size while also providing a natural framework to model process error...
Non-parametric approach to the study of phenotypic stability.
Ferreira, D F; Fernandes, S B; Bruzi, A T; Ramalho, M A P
2016-02-19
The aim of this study was to undertake the theoretical derivations of non-parametric methods, which use linear regressions based on rank order, for stability analyses. These methods were extension different parametric methods used for stability analyses and the result was compared with a standard non-parametric method. Intensive computational methods (e.g., bootstrap and permutation) were applied, and data from the plant-breeding program of the Biology Department of UFLA (Minas Gerais, Brazil) were used to illustrate and compare the tests. The non-parametric stability methods were effective for the evaluation of phenotypic stability. In the presence of variance heterogeneity, the non-parametric methods exhibited greater power of discrimination when determining the phenotypic stability of genotypes.
PV power forecast using a nonparametric PV model
Almeida, Marcelo Pinho; Perpiñan Lamigueiro, Oscar; Narvarte Fernández, Luis
2015-01-01
Forecasting the AC power output of a PV plant accurately is important both for plant owners and electric system operators. Two main categories of PV modeling are available: the parametric and the nonparametric. In this paper, a methodology using a nonparametric PV model is proposed, using as inputs several forecasts of meteorological variables from a Numerical Weather Forecast model, and actual AC power measurements of PV plants. The methodology was built upon the R environment and uses Quant...
Nonparametric Kernel Smoothing Methods. The sm library in Xlisp-Stat
Directory of Open Access Journals (Sweden)
Luca Scrucca
2001-06-01
Full Text Available In this paper we describe the Xlisp-Stat version of the sm library, a software for applying nonparametric kernel smoothing methods. The original version of the sm library was written by Bowman and Azzalini in S-Plus, and it is documented in their book Applied Smoothing Techniques for Data Analysis (1997. This is also the main reference for a complete description of the statistical methods implemented. The sm library provides kernel smoothing methods for obtaining nonparametric estimates of density functions and regression curves for different data structures. Smoothing techniques may be employed as a descriptive graphical tool for exploratory data analysis. Furthermore, they can also serve for inferential purposes as, for instance, when a nonparametric estimate is used for checking a proposed parametric model. The Xlisp-Stat version includes some extensions to the original sm library, mainly in the area of local likelihood estimation for generalized linear models. The Xlisp-Stat version of the sm library has been written following an object-oriented approach. This should allow experienced Xlisp-Stat users to implement easily their own methods and new research ideas into the built-in prototypes.
Landau-Zener Probability Reviewed
Valencia, C
2008-01-01
We examine the survival probability for neutrino propagation through matter with variable density. We present a new method to calculate the level-crossing probability that differs from Landau's method by constant factor, which is relevant in the interpretation of neutrino flux from supernova explosion.
Morton, Kenneth D., Jr.; Torrione, Peter A.; Collins, Leslie
2010-04-01
Time domain ground penetrating radar (GPR) has been shown to be a powerful sensing phenomenology for detecting buried objects such as landmines. Landmine detection with GPR data typically utilizes a feature-based pattern classification algorithm to discriminate buried landmines from other sub-surface objects. In high-fidelity GPR, the time-frequency characteristics of a landmine response should be indicative of the physical construction and material composition of the landmine and could therefore be useful for discrimination from other non-threatening sub-surface objects. In this research we propose modeling landmine time-domain responses with a nonparametric Bayesian time-series model and we perform clustering of these time-series models with a hierarchical nonparametric Bayesian model. Each time-series is modeled as a hidden Markov model (HMM) with autoregressive (AR) state densities. The proposed nonparametric Bayesian prior allows for automated learning of the number of states in the HMM as well as the AR order within each state density. This creates a flexible time-series model with complexity determined by the data. Furthermore, a hierarchical non-parametric Bayesian prior is used to group landmine responses with similar HMM model parameters, thus learning the number of distinct landmine response models within a data set. Model inference is accomplished using a fast variational mean field approximation that can be implemented for on-line learning.
Akhtar, Naveed; Mian, Ajmal
2017-10-03
We present a principled approach to learn a discriminative dictionary along a linear classifier for hyperspectral classification. Our approach places Gaussian Process priors over the dictionary to account for the relative smoothness of the natural spectra, whereas the classifier parameters are sampled from multivariate Gaussians. We employ two Beta-Bernoulli processes to jointly infer the dictionary and the classifier. These processes are coupled under the same sets of Bernoulli distributions. In our approach, these distributions signify the frequency of the dictionary atom usage in representing class-specific training spectra, which also makes the dictionary discriminative. Due to the coupling between the dictionary and the classifier, the popularity of the atoms for representing different classes gets encoded into the classifier. This helps in predicting the class labels of test spectra that are first represented over the dictionary by solving a simultaneous sparse optimization problem. The labels of the spectra are predicted by feeding the resulting representations to the classifier. Our approach exploits the nonparametric Bayesian framework to automatically infer the dictionary size--the key parameter in discriminative dictionary learning. Moreover, it also has the desirable property of adaptively learning the association between the dictionary atoms and the class labels by itself. We use Gibbs sampling to infer the posterior probability distributions over the dictionary and the classifier under the proposed model, for which, we derive analytical expressions. To establish the effectiveness of our approach, we test it on benchmark hyperspectral images. The classification performance is compared with the state-of-the-art dictionary learning-based classification methods.
Institute of Scientific and Technical Information of China (English)
陈亮; 程汉文; 吴乐南
2009-01-01
依据星座图采用非参数贝叶斯方法对多元相移键控(MPSK)信号进行调制识别.将未知信噪比(SNR)水平的MPSK信号看成复平面内多个未知均值和方差的高斯分布依照一定的比例混合而成,利用非参数贝叶斯推断方法进行密度估计,实现对MPSK信号分类目的.推断过程中,引入Dirichlet过程作为混合比例因子的先验分布,结合正态逆Wishart(NIW)分布作为均值和方差的先验分布,根据接收信号,利用Gibbs采样的MCMC(Monte Carlo Markov chain)随机采样算法,不断调整混合比例因子、均值和方差.通过多次迭代,得到对调制信号的密度估计.仿真表明,在SNR>5 dB,码元数目大于1 600时,2/4/8PSK的识别率超过了95%.%A nonparametric Bayesian method is presented to classify the MPSK (M-ary phase shift keying) signals. The MPSK signals with unknown signal noise ratios (SNRs) are modeled as a Gaussian mixture model with unknown means and covariances in the constellation plane, and a clustering method is proposed to estimate the probability density of the MPSK signals. The method is based on the nonparametric Bayesian inference, which introduces the Dirichlet process as the prior probability of the mixture coefficient, and applies a normal inverse Wishart (NIW) distribution as the prior probability of the unknown mean and covariance. Then, according to the received signals, the parameters are adjusted by the Monte Carlo Markov chain (MCMC) random sampling algorithm. By iterations, the density estimation of the MPSK signals can be estimated. Simulation results show that the correct recognition ratio of 2/4/8PSK is greater than 95% under the condition that SNR >5 dB and 1 600 symbols are used in this method.
Propensity, Probability, and Quantum Theory
Ballentine, Leslie E.
2016-08-01
Quantum mechanics and probability theory share one peculiarity. Both have well established mathematical formalisms, yet both are subject to controversy about the meaning and interpretation of their basic concepts. Since probability plays a fundamental role in QM, the conceptual problems of one theory can affect the other. We first classify the interpretations of probability into three major classes: (a) inferential probability, (b) ensemble probability, and (c) propensity. Class (a) is the basis of inductive logic; (b) deals with the frequencies of events in repeatable experiments; (c) describes a form of causality that is weaker than determinism. An important, but neglected, paper by P. Humphreys demonstrated that propensity must differ mathematically, as well as conceptually, from probability, but he did not develop a theory of propensity. Such a theory is developed in this paper. Propensity theory shares many, but not all, of the axioms of probability theory. As a consequence, propensity supports the Law of Large Numbers from probability theory, but does not support Bayes theorem. Although there are particular problems within QM to which any of the classes of probability may be applied, it is argued that the intrinsic quantum probabilities (calculated from a state vector or density matrix) are most naturally interpreted as quantum propensities. This does not alter the familiar statistical interpretation of QM. But the interpretation of quantum states as representing knowledge is untenable. Examples show that a density matrix fails to represent knowledge.
Methodology in robust and nonparametric statistics
Jurecková, Jana; Picek, Jan
2012-01-01
Introduction and SynopsisIntroductionSynopsisPreliminariesIntroductionInference in Linear ModelsRobustness ConceptsRobust and Minimax Estimation of LocationClippings from Probability and Asymptotic TheoryProblemsRobust Estimation of Location and RegressionIntroductionM-EstimatorsL-EstimatorsR-EstimatorsMinimum Distance and Pitman EstimatorsDifferentiable Statistical FunctionsProblemsAsymptotic Representations for L-Estimators
Ohkubo, Jun
2011-12-01
A scheme is developed for estimating state-dependent drift and diffusion coefficients in a stochastic differential equation from time-series data. The scheme does not require to specify parametric forms for the drift and diffusion coefficients in advance. In order to perform the nonparametric estimation, a maximum likelihood method is combined with a concept based on a kernel density estimation. In order to deal with discrete observation or sparsity of the time-series data, a local linearization method is employed, which enables a fast estimation.
7th High Dimensional Probability Meeting
Mason, David; Reynaud-Bouret, Patricia; Rosinski, Jan
2016-01-01
This volume collects selected papers from the 7th High Dimensional Probability meeting held at the Institut d'Études Scientifiques de Cargèse (IESC) in Corsica, France. High Dimensional Probability (HDP) is an area of mathematics that includes the study of probability distributions and limit theorems in infinite-dimensional spaces such as Hilbert spaces and Banach spaces. The most remarkable feature of this area is that it has resulted in the creation of powerful new tools and perspectives, whose range of application has led to interactions with other subfields of mathematics, statistics, and computer science. These include random matrices, nonparametric statistics, empirical processes, statistical learning theory, concentration of measure phenomena, strong and weak approximations, functional estimation, combinatorial optimization, and random graphs. The contributions in this volume show that HDP theory continues to thrive and develop new tools, methods, techniques and perspectives to analyze random phenome...
A non-parametric Bayesian approach for clustering and tracking non-stationarities of neural spikes.
Shalchyan, Vahid; Farina, Dario
2014-02-15
Neural spikes from multiple neurons recorded in a multi-unit signal are usually separated by clustering. Drifts in the position of the recording electrode relative to the neurons over time cause gradual changes in the position and shapes of the clusters, challenging the clustering task. By dividing the data into short time intervals, Bayesian tracking of the clusters based on Gaussian cluster model has been previously proposed. However, the Gaussian cluster model is often not verified for neural spikes. We present a Bayesian clustering approach that makes no assumptions on the distribution of the clusters and use kernel-based density estimation of the clusters in every time interval as a prior for Bayesian classification of the data in the subsequent time interval. The proposed method was tested and compared to Gaussian model-based approach for cluster tracking by using both simulated and experimental datasets. The results showed that the proposed non-parametric kernel-based density estimation of the clusters outperformed the sequential Gaussian model fitting in both simulated and experimental data tests. Using non-parametric kernel density-based clustering that makes no assumptions on the distribution of the clusters enhances the ability of tracking cluster non-stationarity over time with respect to the Gaussian cluster modeling approach. Copyright © 2013 Elsevier B.V. All rights reserved.
Asymptotic theory of nonparametric regression estimates with censored data
Institute of Scientific and Technical Information of China (English)
无
2000-01-01
For regression analysis, some useful information may have been lost when the responses are right censored. To estimate nonparametric functions, several estimates based on censored data have been proposed and their consistency and convergence rates have been studied in literature, but the optimal rates of global convergence have not been obtained yet. Because of the possible information loss, one may think that it is impossible for an estimate based on censored data to achieve the optimal rates of global convergence for nonparametric regression, which were established by Stone based on complete data. This paper constructs a regression spline estimate of a general nonparametric regression function based on right_censored response data, and proves, under some regularity conditions, that this estimate achieves the optimal rates of global convergence for nonparametric regression. Since the parameters for the nonparametric regression estimate have to be chosen based on a data driven criterion, we also obtain the asymptotic optimality of AIC, AICC, GCV, Cp and FPE criteria in the process of selecting the parameters.
Comparing parametric and nonparametric regression methods for panel data
DEFF Research Database (Denmark)
Czekaj, Tomasz Gerard; Henningsen, Arne
We investigate and compare the suitability of parametric and non-parametric stochastic regression methods for analysing production technologies and the optimal firm size. Our theoretical analysis shows that the most commonly used functional forms in empirical production analysis, Cobb-Douglas and......We investigate and compare the suitability of parametric and non-parametric stochastic regression methods for analysing production technologies and the optimal firm size. Our theoretical analysis shows that the most commonly used functional forms in empirical production analysis, Cobb......-Douglas and Translog, are unsuitable for analysing the optimal firm size. We show that the Translog functional form implies an implausible linear relationship between the (logarithmic) firm size and the elasticity of scale, where the slope is artificially related to the substitutability between the inputs...... rejects both the Cobb-Douglas and the Translog functional form, while a recently developed nonparametric kernel regression method with a fully nonparametric panel data specification delivers plausible results. On average, the nonparametric regression results are similar to results that are obtained from...
Generalized Probability Functions
Directory of Open Access Journals (Sweden)
Alexandre Souto Martinez
2009-01-01
Full Text Available From the integration of nonsymmetrical hyperboles, a one-parameter generalization of the logarithmic function is obtained. Inverting this function, one obtains the generalized exponential function. Motivated by the mathematical curiosity, we show that these generalized functions are suitable to generalize some probability density functions (pdfs. A very reliable rank distribution can be conveniently described by the generalized exponential function. Finally, we turn the attention to the generalization of one- and two-tail stretched exponential functions. We obtain, as particular cases, the generalized error function, the Zipf-Mandelbrot pdf, the generalized Gaussian and Laplace pdf. Their cumulative functions and moments were also obtained analytically.
Rotondi, R.
2009-04-01
According to the unified scaling theory the probability distribution function of the recurrence time T is a scaled version of a base function and the average value of T can be used as a scale parameter for the distribution. The base function must belong to the scale family of distributions: tested on different catalogues and for different scale levels, for Corral (2005) the (truncated) generalized gamma distribution is the best model, for German (2006) the Weibull distribution. The scaling approach should overcome the difficulty of estimating distribution functions over small areas but theorical limitations and partial instability of the estimated distributions have been pointed out in the literature. Our aim is to analyze the recurrence time of strong earthquakes that occurred in the Italian territory. To satisfy the hypotheses of independence and identical distribution we have evaluated the times between events that occurred in each area of the Database of Individual Seismogenic Sources and then we have gathered them by eight tectonically coherent regions, each of them dominated by a well characterized geodynamic process. To solve problems like: paucity of data, presence of outliers and uncertainty in the choice of the functional expression for the distribution of t, we have followed a nonparametric approach (Rotondi (2009)) in which: (a) the maximum flexibility is obtained by assuming that the probability distribution is a random function belonging to a large function space, distributed as a stochastic process; (b) nonparametric estimation method is robust when the data contain outliers; (c) Bayesian methodology allows to exploit different information sources so that the model fitting may be good also to scarce samples. We have compared the hazard rates evaluated through the parametric and nonparametric approach. References Corral A. (2005). Mixing of rescaled data and Bayesian inference for earthquake recurrence times, Nonlin. Proces. Geophys., 12, 89
Institute of Scientific and Technical Information of China (English)
邓厚斌; 葛毅; 范璐敏; 刘晓雯; 李盈盈
2012-01-01
In order to proceed depreciation accounting of medical equipment reasonably, this paper analyses and compares the advantages and disadvantages of several common depreciation methods, with use efficiency of medical equipment, proposes distribution rule of static depreciation rate of x2 distribution probability density function, meanwhile, introduces benchmark benefit ratio of funds, establishes dynamic depreciation method of medical equipment.%为能够较合理地进行医疗设备的折旧核算,本文分析比较了常见的几种折旧方法的优缺点,结合医疗设备的使用效能,提出了医疗设备拟合x 2分布概率密度函数的静态折旧率分布规律,建立新的医疗设备折旧法.
Predicting Market Impact Costs Using Nonparametric Machine Learning Models.
Directory of Open Access Journals (Sweden)
Saerom Park
Full Text Available Market impact cost is the most significant portion of implicit transaction costs that can reduce the overall transaction cost, although it cannot be measured directly. In this paper, we employed the state-of-the-art nonparametric machine learning models: neural networks, Bayesian neural network, Gaussian process, and support vector regression, to predict market impact cost accurately and to provide the predictive model that is versatile in the number of variables. We collected a large amount of real single transaction data of US stock market from Bloomberg Terminal and generated three independent input variables. As a result, most nonparametric machine learning models outperformed a-state-of-the-art benchmark parametric model such as I-star model in four error measures. Although these models encounter certain difficulties in separating the permanent and temporary cost directly, nonparametric machine learning models can be good alternatives in reducing transaction costs by considerably improving in prediction performance.
Predicting Market Impact Costs Using Nonparametric Machine Learning Models.
Park, Saerom; Lee, Jaewook; Son, Youngdoo
2016-01-01
Market impact cost is the most significant portion of implicit transaction costs that can reduce the overall transaction cost, although it cannot be measured directly. In this paper, we employed the state-of-the-art nonparametric machine learning models: neural networks, Bayesian neural network, Gaussian process, and support vector regression, to predict market impact cost accurately and to provide the predictive model that is versatile in the number of variables. We collected a large amount of real single transaction data of US stock market from Bloomberg Terminal and generated three independent input variables. As a result, most nonparametric machine learning models outperformed a-state-of-the-art benchmark parametric model such as I-star model in four error measures. Although these models encounter certain difficulties in separating the permanent and temporary cost directly, nonparametric machine learning models can be good alternatives in reducing transaction costs by considerably improving in prediction performance.
Comparing parametric and nonparametric regression methods for panel data
DEFF Research Database (Denmark)
Czekaj, Tomasz Gerard; Henningsen, Arne
We investigate and compare the suitability of parametric and non-parametric stochastic regression methods for analysing production technologies and the optimal firm size. Our theoretical analysis shows that the most commonly used functional forms in empirical production analysis, Cobb......-Douglas and Translog, are unsuitable for analysing the optimal firm size. We show that the Translog functional form implies an implausible linear relationship between the (logarithmic) firm size and the elasticity of scale, where the slope is artificially related to the substitutability between the inputs....... The practical applicability of the parametric and non-parametric regression methods is scrutinised and compared by an empirical example: we analyse the production technology and investigate the optimal size of Polish crop farms based on a firm-level balanced panel data set. A nonparametric specification test...
Probability of Failure in Random Vibration
DEFF Research Database (Denmark)
Nielsen, Søren R.K.; Sørensen, John Dalsgaard
1988-01-01
Close approximations to the first-passage probability of failure in random vibration can be obtained by integral equation methods. A simple relation exists between the first-passage probability density function and the distribution function for the time interval spent below a barrier before out......-crossing. An integral equation for the probability density function of the time interval is formulated, and adequate approximations for the kernel are suggested. The kernel approximation results in approximate solutions for the probability density function of the time interval and thus for the first-passage probability...
Probability Aggregates in Probability Answer Set Programming
Saad, Emad
2013-01-01
Probability answer set programming is a declarative programming that has been shown effective for representing and reasoning about a variety of probability reasoning tasks. However, the lack of probability aggregates, e.g. {\\em expected values}, in the language of disjunctive hybrid probability logic programs (DHPP) disallows the natural and concise representation of many interesting problems. In this paper, we extend DHPP to allow arbitrary probability aggregates. We introduce two types of p...
Non-parametric determination of H and He interstellar fluxes from cosmic-ray data
Ghelfi, A.; Barao, F.; Derome, L.; Maurin, D.
2016-06-01
Context. Top-of-atmosphere (TOA) cosmic-ray (CR) fluxes from satellites and balloon-borne experiments are snapshots of the solar activity imprinted on the interstellar (IS) fluxes. Given a series of snapshots, the unknown IS flux shape and the level of modulation (for each snapshot) can be recovered. Aims: We wish (i) to provide the most accurate determination of the IS H and He fluxes from TOA data alone; (ii) to obtain the associated modulation levels (and uncertainties) while fully accounting for the correlations with the IS flux uncertainties; and (iii) to inspect whether the minimal force-field approximation is sufficient to explain all the data at hand. Methods: Using H and He TOA measurements, including the recent high-precision AMS, BESS-Polar, and PAMELA data, we performed a non-parametric fit of the IS fluxes JISH,~He and modulation level φi for each data-taking period. We relied on a Markov chain Monte Carlo (MCMC) engine to extract the probability density function and correlations (hence the credible intervals) of the sought parameters. Results: Although H and He are the most abundant and best measured CR species, several datasets had to be excluded from the analysis because of inconsistencies with other measurements. From the subset of data passing our consistency cut, we provide ready-to-use best-fit and credible intervals for the H and He IS fluxes from MeV/n to PeV/n energy (with a relative precision in the range [ 2-10% ] at 1σ). Given the strong correlation between JIS and φi parameters, the uncertainties on JIS translate into Δφ ≈ ± 30 MV (at 1σ) for all experiments. We also find that the presence of 3He in He data biases φ towards higher φ values by ~30 MV. The force-field approximation, despite its limitation, gives an excellent (χ2/d.o.f. = 1.02) description of the recent high-precision TOA H and He fluxes. Conclusions: The analysis must be extended to different charge species and more realistic modulation models. It would benefit
Nonparametric estimation of a convex bathtub-shaped hazard function.
Jankowski, Hanna K; Wellner, Jon A
2009-11-01
In this paper, we study the nonparametric maximum likelihood estimator (MLE) of a convex hazard function. We show that the MLE is consistent and converges at a local rate of n(2/5) at points x(0) where the true hazard function is positive and strictly convex. Moreover, we establish the pointwise asymptotic distribution theory of our estimator under these same assumptions. One notable feature of the nonparametric MLE studied here is that no arbitrary choice of tuning parameter (or complicated data-adaptive selection of the tuning parameter) is required.
Institute of Scientific and Technical Information of China (English)
束锋; 李隽; 顾晨; 王进; 周叶; 徐彦青; 钱玉文
2015-01-01
大规模M IM O系统中，相对于其他基于信道矩阵分解的波束成形算法，如迫零、最小均方误差算法等，匹配滤波（Matched filter ，MF）具有复杂度极低的优点，从而成为一种极具实用潜力的波束成形算法。鉴于此，本文推导了基站采用M F波束成形算法时，用户端信干噪比（Signal‐to‐interference‐and‐noise ratio ，SINR）的近似概率密度函数（Probability density function ，PDF）。该函数对于推导与分析系统性能，如和速率、中断概率等至关重要。仿真表明：当基站天线数趋于大规模时，SINR公式的PDF曲线趋近于通过纯仿真得到的PDF曲线。%In massive MIMO systems ,the matched filter (MF) beamformer is an attractive technique due to its extremely low complexity compared with the high‐complexity decomposition‐based beamforming techniques ,such as zero forcing and minimum mean square error .An approximate formula is derived for probability density function (PDF) of the signal‐to‐interference‐and‐noise ratio (SINR) at user terminal when multiple antennas and the MF beamformer are used at the base station .The formula is important in calculating or analyzing system performance such as sum‐rate and outage probability .Simulations exhibit that the difference between the derived approximate formula for PDF and the simulated PDF approaches zero while the number of antennas at the base station tends to large‐scale .
Probability theory and mathematical statistics for engineers
Pugachev, V S
1984-01-01
Probability Theory and Mathematical Statistics for Engineers focuses on the concepts of probability theory and mathematical statistics for finite-dimensional random variables.The publication first underscores the probabilities of events, random variables, and numerical characteristics of random variables. Discussions focus on canonical expansions of random vectors, second-order moments of random vectors, generalization of the density concept, entropy of a distribution, direct evaluation of probabilities, and conditional probabilities. The text then examines projections of random vector
Scaling Qualitative Probability
Burgin, Mark
2017-01-01
There are different approaches to qualitative probability, which includes subjective probability. We developed a representation of qualitative probability based on relational systems, which allows modeling uncertainty by probability structures and is more coherent than existing approaches. This setting makes it possible proving that any comparative probability is induced by some probability structure (Theorem 2.1), that classical probability is a probability structure (Theorem 2.2) and that i...
Nonparametric Cointegration Analysis of Fractional Systems With Unknown Integration Orders
DEFF Research Database (Denmark)
Nielsen, Morten Ørregaard
2009-01-01
In this paper a nonparametric variance ratio testing approach is proposed for determining the number of cointegrating relations in fractionally integrated systems. The test statistic is easily calculated without prior knowledge of the integration order of the data, the strength of the cointegrating...
Non-parametric analysis of rating transition and default data
DEFF Research Database (Denmark)
Fledelius, Peter; Lando, David; Perch Nielsen, Jens
2004-01-01
We demonstrate the use of non-parametric intensity estimation - including construction of pointwise confidence sets - for analyzing rating transition data. We find that transition intensities away from the class studied here for illustration strongly depend on the direction of the previous move b...... but that this dependence vanishes after 2-3 years....
A non-parametric model for the cosmic velocity field
Branchini, E; Teodoro, L; Frenk, CS; Schmoldt, [No Value; Efstathiou, G; White, SDM; Saunders, W; Sutherland, W; Rowan-Robinson, M; Keeble, O; Tadros, H; Maddox, S; Oliver, S
1999-01-01
We present a self-consistent non-parametric model of the local cosmic velocity field derived from the distribution of IRAS galaxies in the PSCz redshift survey. The survey has been analysed using two independent methods, both based on the assumptions of gravitational instability and linear biasing.
Influence of test and person characteristics on nonparametric appropriateness measurement
Meijer, Rob R.; Molenaar, Ivo W.; Sijtsma, Klaas
1994-01-01
Appropriateness measurement in nonparametric item response theory modeling is affected by the reliability of the items, the test length, the type of aberrant response behavior, and the percentage of aberrant persons in the group. The percentage of simulees defined a priori as aberrant responders tha
Influence of Test and Person Characteristics on Nonparametric Appropriateness Measurement
Meijer, Rob R; Molenaar, Ivo W; Sijtsma, Klaas
1994-01-01
Appropriateness measurement in nonparametric item response theory modeling is affected by the reliability of the items, the test length, the type of aberrant response behavior, and the percentage of aberrant persons in the group. The percentage of simulees defined a priori as aberrant responders tha
Estimation of Spatial Dynamic Nonparametric Durbin Models with Fixed Effects
Qian, Minghui; Hu, Ridong; Chen, Jianwei
2016-01-01
Spatial panel data models have been widely studied and applied in both scientific and social science disciplines, especially in the analysis of spatial influence. In this paper, we consider the spatial dynamic nonparametric Durbin model (SDNDM) with fixed effects, which takes the nonlinear factors into account base on the spatial dynamic panel…
Non-parametric Bayesian inference for inhomogeneous Markov point processes
DEFF Research Database (Denmark)
Berthelsen, Kasper Klitgaard; Møller, Jesper
With reference to a specific data set, we consider how to perform a flexible non-parametric Bayesian analysis of an inhomogeneous point pattern modelled by a Markov point process, with a location dependent first order term and pairwise interaction only. A priori we assume that the first order term...
Investigating the cultural patterns of corruption: A nonparametric analysis
Halkos, George; Tzeremes, Nickolaos
2011-01-01
By using a sample of 77 countries our analysis applies several nonparametric techniques in order to reveal the link between national culture and corruption. Based on Hofstede’s cultural dimensions and the corruption perception index, the results reveal that countries with higher levels of corruption tend to have higher power distance and collectivism values in their society.
Homothetic Efficiency and Test Power: A Non-Parametric Approach
J. Heufer (Jan); P. Hjertstrand (Per)
2015-01-01
markdownabstract__Abstract__ We provide a nonparametric revealed preference approach to demand analysis based on homothetic efficiency. Homotheticity is a useful restriction but data rarely satisfies testable conditions. To overcome this we provide a way to estimate homothetic efficiency of consump
Non-parametric analysis of rating transition and default data
DEFF Research Database (Denmark)
Fledelius, Peter; Lando, David; Perch Nielsen, Jens
2004-01-01
We demonstrate the use of non-parametric intensity estimation - including construction of pointwise confidence sets - for analyzing rating transition data. We find that transition intensities away from the class studied here for illustration strongly depend on the direction of the previous move...
A non-parametric approach to estimate the total deviation index for non-normal data.
Perez-Jaume, Sara; Carrasco, Josep L
2015-11-10
Concordance indices are used to assess the degree of agreement between different methods that measure the same characteristic. In this context, the total deviation index (TDI) is an unscaled concordance measure that quantifies to which extent the readings from the same subject obtained by different methods may differ with a certain probability. Common approaches to estimate the TDI assume data are normally distributed and linearity between response and effects (subjects, methods and random error). Here, we introduce a new non-parametric methodology for estimation and inference of the TDI that can deal with any kind of quantitative data. The present study introduces this non-parametric approach and compares it with the already established methods in two real case examples that represent situations of non-normal data (more specifically, skewed data and count data). The performance of the already established methodologies and our approach in these contexts is assessed by means of a simulation study. Copyright © 2015 John Wiley & Sons, Ltd.
A Bayesian non-parametric Potts model with application to pre-surgical FMRI data.
Johnson, Timothy D; Liu, Zhuqing; Bartsch, Andreas J; Nichols, Thomas E
2013-08-01
The Potts model has enjoyed much success as a prior model for image segmentation. Given the individual classes in the model, the data are typically modeled as Gaussian random variates or as random variates from some other parametric distribution. In this article, we present a non-parametric Potts model and apply it to a functional magnetic resonance imaging study for the pre-surgical assessment of peritumoral brain activation. In our model, we assume that the Z-score image from a patient can be segmented into activated, deactivated, and null classes, or states. Conditional on the class, or state, the Z-scores are assumed to come from some generic distribution which we model non-parametrically using a mixture of Dirichlet process priors within the Bayesian framework. The posterior distribution of the model parameters is estimated with a Markov chain Monte Carlo algorithm, and Bayesian decision theory is used to make the final classifications. Our Potts prior model includes two parameters, the standard spatial regularization parameter and a parameter that can be interpreted as the a priori probability that each voxel belongs to the null, or background state, conditional on the lack of spatial regularization. We assume that both of these parameters are unknown, and jointly estimate them along with other model parameters. We show through simulation studies that our model performs on par, in terms of posterior expected loss, with parametric Potts models when the parametric model is correctly specified and outperforms parametric models when the parametric model in misspecified.
Rojas-Lima, J. E.; Domínguez-Pacheco, A.; Hernández-Aguilar, C.; Cruz-Orea, A.
2016-09-01
Considering the necessity of photothermal alternative approaches for characterizing nonhomogeneous materials like maize seeds, the objective of this research work was to analyze statistically the amplitude variations of photopyroelectric signals, by means of nonparametric techniques such as the histogram and the kernel density estimator, and the probability density function of the amplitude variations of two genotypes of maize seeds with different pigmentations and structural components: crystalline and floury. To determine if the probability density function had a known parametric form, the histogram was determined which did not present a known parametric form, so the kernel density estimator using the Gaussian kernel, with an efficiency of 95 % in density estimation, was used to obtain the probability density function. The results obtained indicated that maize seeds could be differentiated in terms of the statistical values for floury and crystalline seeds such as the mean (93.11, 159.21), variance (1.64× 103, 1.48× 103), and standard deviation (40.54, 38.47) obtained from the amplitude variations of photopyroelectric signals in the case of the histogram approach. For the case of the kernel density estimator, seeds can be differentiated in terms of kernel bandwidth or smoothing constant h of 9.85 and 6.09 for floury and crystalline seeds, respectively.
Cirillo, Pasquale; Muliere, Pietro
2010-01-01
In this paper we propose a new nonparametric approach to interacting failing systems (FS), that is systems whose probability of failure is not negligible in a fixed time horizon, a typical example being firms and financial bonds. The main purpose when studying a FS is to calculate the probability of default and the distribution of the number of failures that may occur during the observation period. A model used to study a failing system is defined default model. In particular, we present a general recursive model constructed by the means of inter- acting urns. After introducing the theoretical model and its properties we show a first application to credit risk modeling, showing how to assess the idiosyncratic probability of default of an obligor and the joint probability of failure of a set of obligors in a portfolio of risks, that are divided into reliability classes.
Comparison of non-parametric methods for ungrouping coarsely aggregated data
DEFF Research Database (Denmark)
Rizzi, Silvia; Thinggaard, Mikael; Engholm, Gerda
2016-01-01
Background Histograms are a common tool to estimate densities non-parametrically. They are extensively encountered in health sciences to summarize data in a compact format. Examples are age-specific distributions of death or onset of diseases grouped in 5-years age classes with an open-ended age...... methods for ungrouping count data. We compare the performance of two spline interpolation methods, two kernel density estimators and a penalized composite link model first via a simulation study and then with empirical data obtained from the NORDCAN Database. All methods analyzed can be used to estimate...... composite link model performs the best. Conclusion We give an overview and test different methods to estimate detailed distributions from grouped count data. Health researchers can benefit from these versatile methods, which are ready for use in the statistical software R. We recommend using the penalized...
Non-parametric Estimation approach in statistical investigation of nuclear spectra
Jafarizadeh, M A; Sabri, H; Maleki, B Rashidian
2011-01-01
In this paper, Kernel Density Estimation (KDE) as a non-parametric estimation method is used to investigate statistical properties of nuclear spectra. The deviation to regular or chaotic dynamics, is exhibited by closer distances to Poisson or Wigner limits respectively which evaluated by Kullback-Leibler Divergence (KLD) measure. Spectral statistics of different sequences prepared by nuclei corresponds to three dynamical symmetry limits of Interaction Boson Model(IBM), oblate and prolate nuclei and also the pairing effect on nuclear level statistics are analyzed (with pure experimental data). KD-based estimated density function, confirm previous predictions with minimum uncertainty (evaluated with Integrate Absolute Error (IAE)) in compare to Maximum Likelihood (ML)-based method. Also, the increasing of regularity degrees of spectra due to pairing effect is reveal.
Directory of Open Access Journals (Sweden)
Akhtar R. Siddique
2000-03-01
Full Text Available This paper develops a filtering-based framework of non-parametric estimation of parameters of a diffusion process from the conditional moments of discrete observations of the process. This method is implemented for interest rate data in the Eurodollar and long term bond markets. The resulting estimates are then used to form non-parametric univariate and bivariate interest rate models and compute prices for the short term Eurodollar interest rate futures options and long term discount bonds. The bivariate model produces prices substantially closer to the market prices. This paper develops a filtering-based framework of non-parametric estimation of parameters of a diffusion process from the conditional moments of discrete observations of the process. This method is implemented for interest rate data in the Eurodollar and long term bond markets. The resulting estimates are then used to form non-parametric univariate and bivariate interest rate models and compute prices for the short term Eurodollar interest rate futures options and long term discount bonds. The bivariate model produces prices substantially closer to the market prices.
Institute of Scientific and Technical Information of China (English)
周云龙; 王芳
2014-01-01
在自行搭建冷态流化床实验台的基础上，采集了不同压力测点处的压力脉动信号。通过对比、分析流化床风帽入口与床壁测点处压力信号的频谱图，得到了不同压力测点传达相同流动特性信息的结论。结合Welch算法的谱估计和t分布下的概率密度函数，对所采集到的压力脉动信号进行累积概率分布的对比和分析。结果表明：在压力信号Welch谱估计的能量累积概率分布图中，能够很容易地观察到流化床内流动状态的变化，为以后识别多相流流型提供了新的途径。%Basing on the self-designed fluidized bed experimental rig, the pressure fluctuation signals at differ-ent pressure test points were collected.Through comparing and analyzing the recurrence plots of pressure sig-nals at different test points, the conclusion that pressure signals at different test points convey the same infor-mation of flow characteristics was reached.Having the probability density function under the Student’ s t-distri-bution combined with the spectral estimation of Welch algorithm to contrast and analyze the cumulative proba-bility distributions of pressure fluctuant signals shows that, in the energy cumulative probability distribution map of Welch spectrum estimation, the changing of flow state in fluidized bed can be easily observed, this pro-vides a new approach to the identification of multiphase flow.
Energy Technology Data Exchange (ETDEWEB)
Varella, Marcio Teixeira do Nascimento
2001-12-15
We have calculated annihilation probability densities (APD) for positron collisions against He atom and H{sub 2} molecule. It was found that direct annihilation prevails at low energies, while annihilation following virtual positronium (Ps) formation is the dominant mechanism at higher energies. In room-temperature collisions (10{sup -2} eV) the APD spread over a considerable extension, being quite similar to the electronic densities of the targets. The capture of the positron in an electronic Feshbach resonance strongly enhanced the annihilation rate in e{sup +}-H{sub 2} collisions. We also discuss strategies to improve the calculation of the annihilation parameter (Z{sub eff} ), after debugging the computational codes of the Schwinger Multichannel Method (SMC). Finally, we consider the inclusion of the Ps formation channel in the SMC and show that effective configurations (pseudo eigenstates of the Hamiltonian of the collision ) are able to significantly reduce the computational effort in positron scattering calculations. Cross sections for electron scattering by polyatomic molecules were obtained in three different approximations: static-exchange (SE); tatic-exchange-plus-polarization (SEP); and multichannel coupling. The calculations for polar targets were improved through the rotational resolution of scattering amplitudes in which the SMC was combined with the first Born approximation (FBA). In general, elastic cross sections (SE and SEP approximations) showed good agreement with available experimental data for several targets. Multichannel calculations for e{sup -} -H{sub 2}O scattering, on the other hand, presented spurious structures at the electronic excitation thresholds (author)
Comparison of Rank Analysis of Covariance and Nonparametric Randomized Blocks Analysis.
Porter, Andrew C.; McSweeney, Maryellen
The relative power of three possible experimental designs under the condition that data is to be analyzed by nonparametric techniques; the comparison of the power of each nonparametric technique to its parametric analogue; and the comparison of relative powers using nonparametric and parametric techniques are discussed. The three nonparametric…
Briggs, William M.
2012-01-01
The probability leakage of model M with respect to evidence E is defined. Probability leakage is a kind of model error. It occurs when M implies that events $y$, which are impossible given E, have positive probability. Leakage does not imply model falsification. Models with probability leakage cannot be calibrated empirically. Regression models, which are ubiquitous in statistical practice, often evince probability leakage.
Deshler, Terry
2016-04-01
Balloon-borne optical particle counters were used to make in situ size resolved particle concentration measurements within polar stratospheric clouds (PSCs) over 20 years in the Antarctic and over 10 years in the Arctic. The measurements were made primarily during the late winter in the Antarctic and in the early and mid-winter in the Arctic. Measurements in early and mid-winter were also made during 5 years in the Antarctic. For the analysis bimodal lognormal size distributions are fit to 250 meter averages of the particle concentration data. The characteristics of these fits, along with temperature, water and nitric acid vapor mixing ratios, are used to classify the PSC observations as either NAT, STS, ice, or some mixture of these. The vapor mixing ratios are obtained from satellite when possible, otherwise assumptions are made. This classification of the data is used to construct probability density functions for NAT, STS, and ice number concentration, median radius and distribution width for mid and late winter clouds in the Antarctic and for early and mid-winter clouds in the Arctic. Additional analysis is focused on characterizing the temperature histories associated with the particle classes and the different time periods. The results from theses analyses will be presented, and should be useful to set bounds for retrievals of PSC properties from remote measurements, and to constrain model representations of PSCs.
MEASURING DARK MATTER PROFILES NON-PARAMETRICALLY IN DWARF SPHEROIDALS: AN APPLICATION TO DRACO
Energy Technology Data Exchange (ETDEWEB)
Jardel, John R.; Gebhardt, Karl [Department of Astronomy, The University of Texas, 2515 Speedway, Stop C1400, Austin, TX 78712-1205 (United States); Fabricius, Maximilian H.; Williams, Michael J. [Max-Planck Institut fuer extraterrestrische Physik, Giessenbachstrasse, D-85741 Garching bei Muenchen (Germany); Drory, Niv, E-mail: jardel@astro.as.utexas.edu [Instituto de Astronomia, Universidad Nacional Autonoma de Mexico, Avenida Universidad 3000, Ciudad Universitaria, C.P. 04510 Mexico D.F. (Mexico)
2013-02-15
We introduce a novel implementation of orbit-based (or Schwarzschild) modeling that allows dark matter density profiles to be calculated non-parametrically in nearby galaxies. Our models require no assumptions to be made about velocity anisotropy or the dark matter profile. The technique can be applied to any dispersion-supported stellar system, and we demonstrate its use by studying the Local Group dwarf spheroidal galaxy (dSph) Draco. We use existing kinematic data at larger radii and also present 12 new radial velocities within the central 13 pc obtained with the VIRUS-W integral field spectrograph on the 2.7 m telescope at McDonald Observatory. Our non-parametric Schwarzschild models find strong evidence that the dark matter profile in Draco is cuspy for 20 {<=} r {<=} 700 pc. The profile for r {>=} 20 pc is well fit by a power law with slope {alpha} = -1.0 {+-} 0.2, consistent with predictions from cold dark matter simulations. Our models confirm that, despite its low baryon content relative to other dSphs, Draco lives in a massive halo.
Koo, Reginald; Jones, Martin L.
2011-01-01
Quite a number of interesting problems in probability feature an event with probability equal to 1/e. This article discusses three such problems and attempts to explain why this probability occurs with such frequency.
Goldberg, Samuel
1960-01-01
Excellent basic text covers set theory, probability theory for finite sample spaces, binomial theorem, probability distributions, means, standard deviations, probability function of binomial distribution, more. Includes 360 problems with answers for half.
Koo, Reginald; Jones, Martin L.
2011-01-01
Quite a number of interesting problems in probability feature an event with probability equal to 1/e. This article discusses three such problems and attempts to explain why this probability occurs with such frequency.
A Nonparametric Bayesian Approach to Seismic Hazard Modeling Using the ETAS Framework
Ross, G.
2015-12-01
The epidemic-type aftershock sequence (ETAS) model is one of the most popular tools for modeling seismicity and quantifying risk in earthquake-prone regions. Under the ETAS model, the occurrence times of earthquakes are treated as a self-exciting Poisson process where each earthquake briefly increases the probability of subsequent earthquakes occurring soon afterwards, which captures the fact that large mainshocks tend to produce long sequences of aftershocks. A triggering kernel controls the amount by which the probability increases based on the magnitude of each earthquake, and the rate at which it then decays over time. This triggering kernel is usually chosen heuristically, to match the parametric form of the modified Omori law for aftershock decay. However recent work has questioned whether this is an appropriate choice. Since the choice of kernel has a large impact on the predictions made by the ETAS model, avoiding misspecification is crucially important. We present a novel nonparametric version of ETAS which avoids making parametric assumptions, and instead learns the correct specification from the data itself. Our approach is based on the Dirichlet process, which is a modern class of Bayesian prior distribution which allows for efficient inference over an infinite dimensional space of functions. We show how our nonparametric ETAS model can be fit to data, and present results demonstrating that the fit is greatly improved compared to the standard parametric specification. Additionally, we explain how our model can be used to perform probabilistic declustering of earthquake catalogs, to classify earthquakes as being either aftershocks or mainshocks. and to learn the causal relations between pairs of earthquakes.
Nonparametric inference procedures for multistate life table analysis.
Dow, M M
1985-01-01
Recent generalizations of the classical single state life table procedures to the multistate case provide the means to analyze simultaneously the mobility and mortality experience of 1 or more cohorts. This paper examines fairly general nonparametric combinatorial matrix procedures, known as quadratic assignment, as an analysis technic of various transitional patterns commonly generated by cohorts over the life cycle course. To some degree, the output from a multistate life table analysis suggests inference procedures. In his discussion of multstate life table construction features, the author focuses on the matrix formulation of the problem. He then presents several examples of the proposed nonparametric procedures. Data for the mobility and life expectancies at birth matrices come from the 458 member Cayo Santiago rhesus monkey colony. The author's matrix combinatorial approach to hypotheses testing may prove to be a useful inferential strategy in several multidimensional demographic areas.
International Conference on Robust Rank-Based and Nonparametric Methods
McKean, Joseph
2016-01-01
The contributors to this volume include many of the distinguished researchers in this area. Many of these scholars have collaborated with Joseph McKean to develop underlying theory for these methods, obtain small sample corrections, and develop efficient algorithms for their computation. The papers cover the scope of the area, including robust nonparametric rank-based procedures through Bayesian and big data rank-based analyses. Areas of application include biostatistics and spatial areas. Over the last 30 years, robust rank-based and nonparametric methods have developed considerably. These procedures generalize traditional Wilcoxon-type methods for one- and two-sample location problems. Research into these procedures has culminated in complete analyses for many of the models used in practice including linear, generalized linear, mixed, and nonlinear models. Settings are both multivariate and univariate. With the development of R packages in these areas, computation of these procedures is easily shared with r...
Nonparametric instrumental regression with non-convex constraints
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.
Combined parametric-nonparametric identification of block-oriented systems
Mzyk, Grzegorz
2014-01-01
This book considers a problem of block-oriented nonlinear dynamic system identification in the presence of random disturbances. This class of systems includes various interconnections of linear dynamic blocks and static nonlinear elements, e.g., Hammerstein system, Wiener system, Wiener-Hammerstein ("sandwich") system and additive NARMAX systems with feedback. Interconnecting signals are not accessible for measurement. The combined parametric-nonparametric algorithms, proposed in the book, can be selected dependently on the prior knowledge of the system and signals. Most of them are based on the decomposition of the complex system identification task into simpler local sub-problems by using non-parametric (kernel or orthogonal) regression estimation. In the parametric stage, the generalized least squares or the instrumental variables technique is commonly applied to cope with correlated excitations. Limit properties of the algorithms have been shown analytically and illustrated in simple experiments.
Estimation of Stochastic Volatility Models by Nonparametric Filtering
DEFF Research Database (Denmark)
Kanaya, Shin; Kristensen, Dennis
2016-01-01
/estimated volatility process replacing the latent process. Our estimation strategy is applicable to both parametric and nonparametric stochastic volatility models, and can handle both jumps and market microstructure noise. The resulting estimators of the stochastic volatility model will carry additional biases......A two-step estimation method of stochastic volatility models is proposed: In the first step, we nonparametrically estimate the (unobserved) instantaneous volatility process. In the second step, standard estimation methods for fully observed diffusion processes are employed, but with the filtered...... and variances due to the first-step estimation, but under regularity conditions we show that these vanish asymptotically and our estimators inherit the asymptotic properties of the infeasible estimators based on observations of the volatility process. A simulation study examines the finite-sample properties...
Nonparametric Regression Estimation for Multivariate Null Recurrent Processes
Directory of Open Access Journals (Sweden)
Biqing Cai
2015-04-01
Full Text Available This paper discusses nonparametric kernel regression with the regressor being a \\(d\\-dimensional \\(\\beta\\-null recurrent process in presence of conditional heteroscedasticity. We show that the mean function estimator is consistent with convergence rate \\(\\sqrt{n(Th^{d}}\\, where \\(n(T\\ is the number of regenerations for a \\(\\beta\\-null recurrent process and the limiting distribution (with proper normalization is normal. Furthermore, we show that the two-step estimator for the volatility function is consistent. The finite sample performance of the estimate is quite reasonable when the leave-one-out cross validation method is used for bandwidth selection. We apply the proposed method to study the relationship of Federal funds rate with 3-month and 5-year T-bill rates and discover the existence of nonlinearity of the relationship. Furthermore, the in-sample and out-of-sample performance of the nonparametric model is far better than the linear model.
Using non-parametric methods in econometric production analysis
DEFF Research Database (Denmark)
Czekaj, Tomasz Gerard; Henningsen, Arne
-Douglas function nor the Translog function are consistent with the “true” relationship between the inputs and the output in our data set. We solve this problem by using non-parametric regression. This approach delivers reasonable results, which are on average not too different from the results of the parametric......Econometric estimation of production functions is one of the most common methods in applied economic production analysis. These studies usually apply parametric estimation techniques, which obligate the researcher to specify the functional form of the production function. Most often, the Cobb...... results—including measures that are of interest of applied economists, such as elasticities. Therefore, we propose to use nonparametric econometric methods. First, they can be applied to verify the functional form used in parametric estimations of production functions. Second, they can be directly used...
Right-Censored Nonparametric Regression: A Comparative Simulation Study
Directory of Open Access Journals (Sweden)
Dursun Aydın
2016-11-01
Full Text Available This paper introduces the operating of the selection criteria for right-censored nonparametric regression using smoothing spline. In order to transform the response variable into a variable that contains the right-censorship, we used the KaplanMeier weights proposed by [1], and [2]. The major problem in smoothing spline method is to determine a smoothing parameter to obtain nonparametric estimates of the regression function. In this study, the mentioned parameter is chosen based on censored data by means of the criteria such as improved Akaike information criterion (AICc, Bayesian (or Schwarz information criterion (BIC and generalized crossvalidation (GCV. For this purpose, a Monte-Carlo simulation study is carried out to illustrate which selection criterion gives the best estimation for censored data.
Using non-parametric methods in econometric production analysis
DEFF Research Database (Denmark)
Czekaj, Tomasz Gerard; Henningsen, Arne
2012-01-01
by investigating the relationship between the elasticity of scale and the farm size. We use a balanced panel data set of 371~specialised crop farms for the years 2004-2007. A non-parametric specification test shows that neither the Cobb-Douglas function nor the Translog function are consistent with the "true......Econometric estimation of production functions is one of the most common methods in applied economic production analysis. These studies usually apply parametric estimation techniques, which obligate the researcher to specify a functional form of the production function of which the Cobb...... parameter estimates, but also in biased measures which are derived from the parameters, such as elasticities. Therefore, we propose to use non-parametric econometric methods. First, these can be applied to verify the functional form used in parametric production analysis. Second, they can be directly used...
Agreeing Probability Measures for Comparative Probability Structures
P.P. Wakker (Peter)
1981-01-01
textabstractIt is proved that fine and tight comparative probability structures (where the set of events is assumed to be an algebra, not necessarily a σ-algebra) have agreeing probability measures. Although this was often claimed in the literature, all proofs the author encountered are not valid
ANALYSIS OF TIED DATA: AN ALTERNATIVE NON-PARAMETRIC APPROACH
Directory of Open Access Journals (Sweden)
I. C. A. OYEKA
2012-02-01
Full Text Available This paper presents a non-parametric statistical method of analyzing two-sample data that makes provision for the possibility of ties in the data. A test statistic is developed and shown to be free of the effect of any possible ties in the data. An illustrative example is provided and the method is shown to compare favourably with its competitor; the Mann-Whitney test and is more powerful than the latter when there are ties.
Nonparametric test for detecting change in distribution with panel data
Pommeret, Denys; Ghattas, Badih
2011-01-01
This paper considers the problem of comparing two processes with panel data. A nonparametric test is proposed for detecting a monotone change in the link between the two process distributions. The test statistic is of CUSUM type, based on the empirical distribution functions. The asymptotic distribution of the proposed statistic is derived and its finite sample property is examined by bootstrap procedures through Monte Carlo simulations.
A Bayesian nonparametric method for prediction in EST analysis
Directory of Open Access Journals (Sweden)
Prünster Igor
2007-09-01
Full Text Available Abstract Background Expressed sequence tags (ESTs analyses are a fundamental tool for gene identification in organisms. Given a preliminary EST sample from a certain library, several statistical prediction problems arise. In particular, it is of interest to estimate how many new genes can be detected in a future EST sample of given size and also to determine the gene discovery rate: these estimates represent the basis for deciding whether to proceed sequencing the library and, in case of a positive decision, a guideline for selecting the size of the new sample. Such information is also useful for establishing sequencing efficiency in experimental design and for measuring the degree of redundancy of an EST library. Results In this work we propose a Bayesian nonparametric approach for tackling statistical problems related to EST surveys. In particular, we provide estimates for: a the coverage, defined as the proportion of unique genes in the library represented in the given sample of reads; b the number of new unique genes to be observed in a future sample; c the discovery rate of new genes as a function of the future sample size. The Bayesian nonparametric model we adopt conveys, in a statistically rigorous way, the available information into prediction. Our proposal has appealing properties over frequentist nonparametric methods, which become unstable when prediction is required for large future samples. EST libraries, previously studied with frequentist methods, are analyzed in detail. Conclusion The Bayesian nonparametric approach we undertake yields valuable tools for gene capture and prediction in EST libraries. The estimators we obtain do not feature the kind of drawbacks associated with frequentist estimators and are reliable for any size of the additional sample.
Non-parametric versus parametric methods in environmental sciences
Directory of Open Access Journals (Sweden)
Muhammad Riaz
2016-01-01
Full Text Available This current report intends to highlight the importance of considering background assumptions required for the analysis of real datasets in different disciplines. We will provide comparative discussion of parametric methods (that depends on distributional assumptions (like normality relative to non-parametric methods (that are free from many distributional assumptions. We have chosen a real dataset from environmental sciences (one of the application areas. The findings may be extended to the other disciplines following the same spirit.
CRC standard probability and statistics tables and formulae Student ed.
Kokoska, Stephen
2000-01-01
Users of statistics in their professional lives and statistics students will welcome this concise, easy-to-use reference for basic statistics and probability. It contains all of the standardized statistical tables and formulas typically needed plus material on basic statistics topics, such as probability theory and distributions, regression, analysis of variance, nonparametric statistics, and statistical quality control.For each type of distribution the authors supply:?definitions?tables?relationships with other distributions, including limiting forms?statistical parameters, such as variance a
Directory of Open Access Journals (Sweden)
Carlos Alexánder Grajales Correa
2007-07-01
Full Text Available En este trabajo se consideran los rendimientos diarios de un activo financiero con el propósito de modelar y comparar la densidad de probabilidad de la volatilidad estocástica de los retornos. Para tal fin, se proponen los modelos ARCH y sus extensiones, que son en tiempo discreto, así como un modelo empírico de volatilidad estocástica, desarrollado por Paul Wilmott. Para el caso discreto se muestran los modelos que permiten estimar la volatilidad condicional heterocedástica en un instante t del tiempo, t∈[1,T]. En el caso continuo se asocia un proceso de difusión de Itô a la volatilidad estocástica de la serie financiera, lo cual posibilita discretizar dicho proceso y simularlo para obtener densidades de probabilidad empíricas de la volatilidad. Finalmente se ilustran y se comparan los resultados obtenidos con las metodologías expuestas para el caso de las series financieras S&P 500 de EEUU, el Índice de Precios y Cotizaciones de la Bolsa Mexicana de Valores (IPC y el IGBC de Colombia.This work considers daily yields of financial assets in order to model and compare returns stochastic volatility probability density. For such aim, ARCH models and its extensions are proposed - they are in discrete time- as well as an Empirical Stochastic Volatility Model, developed by Paul Wilmott. For the discrete case, models that allow to estimate heteroscedasticity conditional volatility in a time, t, t,t∈[1,T], are shown. In the continuous case, there is an association of an Itô diffusion process to stochastic volatility of the financial series, which allows to write a discretization of this process and to simulate it to obtain empirical probabilistic densities from the volatility. Finally the results are illustrated and compared with methodologies exposed by the case of the financial series S&P 500 of the U.S.A., Index of Prices and Quotations of stock-market Mexican of Values (IPC and IGBC of Colombia.
Institute of Scientific and Technical Information of China (English)
曾波; 邢彦富; 刘章军
2014-01-01
Using the orthogonal expansion method of random processes,the non-stationary seismic acceleration process is represented as a linear combination of the standard orthogonal basis func-tions and the standard orthogonal random variables.Then,using the random function,these stand-ard orthogonal random variables in the orthogonal expansion are expressed as an orthogonal func-tion form of the basic random variable.Therefore,this method can use a basic random variable to express the original earthquake ground processes.The orthogonal expansion-random function ap-proach was used to generate 126 representative earthquake samples,and each representative sam-ple was assigned a given probability.The 126 representative earthquake samples were combined with the probability density evolution method of stochastic dynamical systems and random seis-mic responses of large-scale aqueduct structures was investigated.In this study,four cases were considered;aqueduct without water,aqueduct with water in the central trough,aqueduct with wa-ter in a two-side trough,and aqueduct with water in three troughs,and probability information of seismic responses for these cases were obtained.Moreover,using the proposed method,the seis-mic reliability of the aqueduct structures was efficiently calculated.This method provides a new and effective means for precise seismic analysis of large-scale aqueduct structures.%应用随机过程的正交展开方法，将地震动加速度过程展开为标准正交基函数与标准正交随机变量的线性组合形式。在此基础上采用随机函数的思想，将正交展开式中的标准正交随机变量表达为基本随机变量的函数形式，从而实现用一个基本随机变量来表达原地震动过程的目的。结合地震动过程的正交展开-随机函数模型与概率密度演化方法，对某大型渡槽结构进行随机地震反应分析与抗震可靠度计算；重点研究空槽和三槽有水等四种工况下渡槽结构
Institute of Scientific and Technical Information of China (English)
林再平; 周一宇; 安玮
2013-01-01
基于势概率假设密度滤波(Cardinalized Probability Hypothesis Density,CPHD)检测前跟踪(Track before detect,TBD)算法能有效解决未知目标数的弱小目标检测跟踪.文章深入研究了CPHD算法,从标准CPHD滤波的粒子权重更新出发,结合检测前跟踪的实际,合理地推导出CPHD-TBD算法的粒子权重更新表达式；分析了CPHD滤波目标势分布的物理意义,实现了目标势分布更新计算在检测前跟踪的应用.将CPHD滤波和TBD进行有效结合,提出了基于势概率假设密度滤波的检测前跟踪算法,并给出其详细实现步骤.仿真实验证明提出的CPHD-TBD算法与现有概率假设密度检测前跟踪(PHD-TBD)算法相比,能更详细地传递目标分布信息,从本质上改变了PHD-TBD对目标数估计的方式,能更准确稳定估计目标数,实现了对目标的发现和状态准确估计,性能明显更优.
PHOTOMETRIC REDSHIFTS AND QUASAR PROBABILITIES FROM A SINGLE, DATA-DRIVEN GENERATIVE MODEL
Energy Technology Data Exchange (ETDEWEB)
Bovy, Jo; Hogg, David W.; Weaver, Benjamin A. [Center for Cosmology and Particle Physics, Department of Physics, New York University, 4 Washington Place, New York, NY 10003 (United States); Myers, Adam D. [Department of Physics and Astronomy, University of Wyoming, Laramie, WY 82071 (United States); Hennawi, Joseph F. [Max-Planck-Institut fuer Astronomie, Koenigstuhl 17, D-69117 Heidelberg (Germany); McMahon, Richard G. [Institute of Astronomy, University of Cambridge, Madingley Road, Cambridge CB3 0HA (United Kingdom); Schiminovich, David [Department of Astronomy, Columbia University, New York, NY 10027 (United States); Sheldon, Erin S. [Brookhaven National Laboratory, Upton, NY 11973 (United States); Brinkmann, Jon [Apache Point Observatory, P.O. Box 59, Sunspot, NM 88349 (United States); Schneider, Donald P., E-mail: jo.bovy@nyu.edu [Department of Astronomy and Astrophysics, Pennsylvania State University, 525 Davey Laboratory, University Park, PA 16802 (United States)
2012-04-10
We describe a technique for simultaneously classifying and estimating the redshift of quasars. It can separate quasars from stars in arbitrary redshift ranges, estimate full posterior distribution functions for the redshift, and naturally incorporate flux uncertainties, missing data, and multi-wavelength photometry. We build models of quasars in flux-redshift space by applying the extreme deconvolution technique to estimate the underlying density. By integrating this density over redshift, one can obtain quasar flux densities in different redshift ranges. This approach allows for efficient, consistent, and fast classification and photometric redshift estimation. This is achieved by combining the speed obtained by choosing simple analytical forms as the basis of our density model with the flexibility of non-parametric models through the use of many simple components with many parameters. We show that this technique is competitive with the best photometric quasar classification techniques-which are limited to fixed, broad redshift ranges and high signal-to-noise ratio data-and with the best photometric redshift techniques when applied to broadband optical data. We demonstrate that the inclusion of UV and NIR data significantly improves photometric quasar-star separation and essentially resolves all of the redshift degeneracies for quasars inherent to the ugriz filter system, even when included data have a low signal-to-noise ratio. For quasars spectroscopically confirmed by the SDSS 84% and 97% of the objects with Galaxy Evolution Explorer UV and UKIDSS NIR data have photometric redshifts within 0.1 and 0.3, respectively, of the spectroscopic redshift; this amounts to about a factor of three improvement over ugriz-only photometric redshifts. Our code to calculate quasar probabilities and redshift probability distributions is publicly available.
Photometric redshifts and quasar probabilities from a single, data-driven generative model
Energy Technology Data Exchange (ETDEWEB)
Bovy, Jo [New York Univ. (NYU), NY (United States); Myers, Adam D. [Univ. of Wyoming, Laramie, WY (United States); Max Planck Inst. for Medical Research, Heidelberg (Germany); Hennawi, Joseph F. [Max Planck Inst. for Medical Research, Heidelberg (Germany); Hogg, David W. [Max Planck Inst. for Medical Research, Heidelberg (Germany); New York Univ. (NYU), NY (United States); McMahon, Richard G. [Univ. of Cambridge (United Kingdom); Schiminovich, David [Columbia Univ., New York, NY (United States); Sheldon, Erin S. [Brookhaven National Lab. (BNL), Upton, NY (United States); Brinkmann, Jon [Apache Point Observatory and New Mexico State Univ., Sunspot, NM (United States); Schneider, Donald P. [Pennsylvania State Univ., University Park, PA (United States); Weaver, Benjamin A. [New York Univ. (NYU), NY (United States)
2012-03-20
We describe a technique for simultaneously classifying and estimating the redshift of quasars. It can separate quasars from stars in arbitrary redshift ranges, estimate full posterior distribution functions for the redshift, and naturally incorporate flux uncertainties, missing data, and multi-wavelength photometry. We build models of quasars in flux-redshift space by applying the extreme deconvolution technique to estimate the underlying density. By integrating this density over redshift, one can obtain quasar flux densities in different redshift ranges. This approach allows for efficient, consistent, and fast classification and photometric redshift estimation. This is achieved by combining the speed obtained by choosing simple analytical forms as the basis of our density model with the flexibility of non-parametric models through the use of many simple components with many parameters. We show that this technique is competitive with the best photometric quasar classification techniques—which are limited to fixed, broad redshift ranges and high signal-to-noise ratio data—and with the best photometric redshift techniques when applied to broadband optical data. We demonstrate that the inclusion of UV and NIR data significantly improves photometric quasar-star separation and essentially resolves all of the redshift degeneracies for quasars inherent to the ugriz filter system, even when included data have a low signal-to-noise ratio. For quasars spectroscopically confirmed by the SDSS 84% and 97% of the objects with Galaxy Evolution Explorer UV and UKIDSS NIR data have photometric redshifts within 0.1 and 0.3, respectively, of the spectroscopic redshift; this amounts to about a factor of three improvement over ugriz-only photometric redshifts. Our code to calculate quasar probabilities and redshift probability distributions is publicly available.
A Modified Nonparametric Message Passing Algorithm for Soft Iterative Channel Estimation
Directory of Open Access Journals (Sweden)
Linlin Duan
2013-08-01
Full Text Available Based on the factor graph framework, we derived a Modified Nonparametric Message Passing Algorithm (MNMPA for soft iterative channel estimation in a Low Density Parity-Check (LDPC coded Bit-Interleaved Coded Modulation (BICM system. The algorithm combines ideas from Particle Filtering (PF with popular factor graph techniques. A Markov Chain Monte Carlo (MCMC move step is added after typical sequential Important Sampling (SIS -resampling to prevent particle impoverishment and to improve channel estimation precision. To reduce complexity, a new max-sum rule for updating particle based messages is reformulated and two proper update schedules are designed. Simulation results illustrate the effectiveness of MNMPA and its comparison with other sum-product algorithms in a Gaussian or non-Gaussian noise environment. We also studied the effect of the particle number, pilot symbol spacing and different schedules on BER performance.
Directory of Open Access Journals (Sweden)
Antonio Canale
2017-06-01
Full Text Available msBP is an R package that implements a new method to perform Bayesian multiscale nonparametric inference introduced by Canale and Dunson (2016. The method, based on mixtures of multiscale beta dictionary densities, overcomes the drawbacks of Pólya trees and inherits many of the advantages of Dirichlet process mixture models. The key idea is that an infinitely-deep binary tree is introduced, with a beta dictionary density assigned to each node of the tree. Using a multiscale stick-breaking characterization, stochastically decreasing weights are assigned to each node. The result is an infinite mixture model. The package msBP implements a series of basic functions to deal with this family of priors such as random densities and numbers generation, creation and manipulation of binary tree objects, and generic functions to plot and print the results. In addition, it implements the Gibbs samplers for posterior computation to perform multiscale density estimation and multiscale testing of group differences described in Canale and Dunson (2016.
Probability and Relative Frequency
Drieschner, Michael
2016-01-01
The concept of probability seems to have been inexplicable since its invention in the seventeenth century. In its use in science, probability is closely related with relative frequency. So the task seems to be interpreting that relation. In this paper, we start with predicted relative frequency and show that its structure is the same as that of probability. I propose to call that the `prediction interpretation' of probability. The consequences of that definition are discussed. The "ladder"-structure of the probability calculus is analyzed. The expectation of the relative frequency is shown to be equal to the predicted relative frequency. Probability is shown to be the most general empirically testable prediction.
Elements of probability theory
Rumshiskii, L Z
1965-01-01
Elements of Probability Theory presents the methods of the theory of probability. This book is divided into seven chapters that discuss the general rule for the multiplication of probabilities, the fundamental properties of the subject matter, and the classical definition of probability. The introductory chapters deal with the functions of random variables; continuous random variables; numerical characteristics of probability distributions; center of the probability distribution of a random variable; definition of the law of large numbers; stability of the sample mean and the method of moments
Evaluating probability forecasts
Lai, Tze Leung; Shen, David Bo; 10.1214/11-AOS902
2012-01-01
Probability forecasts of events are routinely used in climate predictions, in forecasting default probabilities on bank loans or in estimating the probability of a patient's positive response to treatment. Scoring rules have long been used to assess the efficacy of the forecast probabilities after observing the occurrence, or nonoccurrence, of the predicted events. We develop herein a statistical theory for scoring rules and propose an alternative approach to the evaluation of probability forecasts. This approach uses loss functions relating the predicted to the actual probabilities of the events and applies martingale theory to exploit the temporal structure between the forecast and the subsequent occurrence or nonoccurrence of the event.
Bayesian Nonparametric Mixture Estimation for Time-Indexed Functional Data in R
Directory of Open Access Journals (Sweden)
Terrance D. Savitsky
2016-08-01
Full Text Available We present growfunctions for R that offers Bayesian nonparametric estimation models for analysis of dependent, noisy time series data indexed by a collection of domains. This data structure arises from combining periodically published government survey statistics, such as are reported in the Current Population Study (CPS. The CPS publishes monthly, by-state estimates of employment levels, where each state expresses a noisy time series. Published state-level estimates from the CPS are composed from household survey responses in a model-free manner and express high levels of volatility due to insufficient sample sizes. Existing software solutions borrow information over a modeled time-based dependence to extract a de-noised time series for each domain. These solutions, however, ignore the dependence among the domains that may be additionally leveraged to improve estimation efficiency. The growfunctions package offers two fully nonparametric mixture models that simultaneously estimate both a time and domain-indexed dependence structure for a collection of time series: (1 A Gaussian process (GP construction, which is parameterized through the covariance matrix, estimates a latent function for each domain. The covariance parameters of the latent functions are indexed by domain under a Dirichlet process prior that permits estimation of the dependence among functions across the domains: (2 An intrinsic Gaussian Markov random field prior construction provides an alternative to the GP that expresses different computation and estimation properties. In addition to performing denoised estimation of latent functions from published domain estimates, growfunctions allows estimation of collections of functions for observation units (e.g., households, rather than aggregated domains, by accounting for an informative sampling design under which the probabilities for inclusion of observation units are related to the response variable. growfunctions includes plot
Probability on real Lie algebras
Franz, Uwe
2016-01-01
This monograph is a progressive introduction to non-commutativity in probability theory, summarizing and synthesizing recent results about classical and quantum stochastic processes on Lie algebras. In the early chapters, focus is placed on concrete examples of the links between algebraic relations and the moments of probability distributions. The subsequent chapters are more advanced and deal with Wigner densities for non-commutative couples of random variables, non-commutative stochastic processes with independent increments (quantum Lévy processes), and the quantum Malliavin calculus. This book will appeal to advanced undergraduate and graduate students interested in the relations between algebra, probability, and quantum theory. It also addresses a more advanced audience by covering other topics related to non-commutativity in stochastic calculus, Lévy processes, and the Malliavin calculus.
The National Aquatic Resource Surveys (NARS) use probability-survey designs to assess the condition of the nation’s waters. In probability surveys (also known as sample-surveys or statistical surveys), sampling sites are selected randomly.
a Multivariate Downscaling Model for Nonparametric Simulation of Daily Flows
Molina, J. M.; Ramirez, J. A.; Raff, D. A.
2011-12-01
A multivariate, stochastic nonparametric framework for stepwise disaggregation of seasonal runoff volumes to daily streamflow is presented. The downscaling process is conditional on volumes of spring runoff and large-scale ocean-atmosphere teleconnections and includes a two-level cascade scheme: seasonal-to-monthly disaggregation first followed by monthly-to-daily disaggregation. The non-parametric and assumption-free character of the framework allows consideration of the random nature and nonlinearities of daily flows, which parametric models are unable to account for adequately. This paper examines statistical links between decadal/interannual climatic variations in the Pacific Ocean and hydrologic variability in US northwest region, and includes a periodicity analysis of climate patterns to detect coherences of their cyclic behavior in the frequency domain. We explore the use of such relationships and selected signals (e.g., north Pacific gyre oscillation, southern oscillation, and Pacific decadal oscillation indices, NPGO, SOI and PDO, respectively) in the proposed data-driven framework by means of a combinatorial approach with the aim of simulating improved streamflow sequences when compared with disaggregated series generated from flows alone. A nearest neighbor time series bootstrapping approach is integrated with principal component analysis to resample from the empirical multivariate distribution. A volume-dependent scaling transformation is implemented to guarantee the summability condition. In addition, we present a new and simple algorithm, based on nonparametric resampling, that overcomes the common limitation of lack of preservation of historical correlation between daily flows across months. The downscaling framework presented here is parsimonious in parameters and model assumptions, does not generate negative values, and produces synthetic series that are statistically indistinguishable from the observations. We present evidence showing that both
Roussas, George G
2006-01-01
Roussas's Introduction to Probability features exceptionally clear explanations of the mathematics of probability theory and explores its diverse applications through numerous interesting and motivational examples. It provides a thorough introduction to the subject for professionals and advanced students taking their first course in probability. The content is based on the introductory chapters of Roussas's book, An Intoduction to Probability and Statistical Inference, with additional chapters and revisions. Written by a well-respected author known for great exposition an
Philosophical theories of probability
Gillies, Donald
2000-01-01
The Twentieth Century has seen a dramatic rise in the use of probability and statistics in almost all fields of research. This has stimulated many new philosophical ideas on probability. Philosophical Theories of Probability is the first book to present a clear, comprehensive and systematic account of these various theories and to explain how they relate to one another. Gillies also offers a distinctive version of the propensity theory of probability, and the intersubjective interpretation, which develops the subjective theory.
Panel data nonparametric estimation of production risk and risk preferences
DEFF Research Database (Denmark)
Czekaj, Tomasz Gerard; Henningsen, Arne
We apply nonparametric panel data kernel regression to investigate production risk, out-put price uncertainty, and risk attitudes of Polish dairy farms based on a firm-level unbalanced panel data set that covers the period 2004–2010. We compare different model specifications and different...... approaches for obtaining firm-specific measures of risk attitudes. We found that Polish dairy farmers are risk averse regarding production risk and price uncertainty. According to our results, Polish dairy farmers perceive the production risk as being more significant than the risk related to output price...
Digital spectral analysis parametric, non-parametric and advanced methods
Castanié, Francis
2013-01-01
Digital Spectral Analysis provides a single source that offers complete coverage of the spectral analysis domain. This self-contained work includes details on advanced topics that are usually presented in scattered sources throughout the literature.The theoretical principles necessary for the understanding of spectral analysis are discussed in the first four chapters: fundamentals, digital signal processing, estimation in spectral analysis, and time-series models.An entire chapter is devoted to the non-parametric methods most widely used in industry.High resolution methods a
Nonparametric statistics a step-by-step approach
Corder, Gregory W
2014-01-01
"…a very useful resource for courses in nonparametric statistics in which the emphasis is on applications rather than on theory. It also deserves a place in libraries of all institutions where introductory statistics courses are taught."" -CHOICE This Second Edition presents a practical and understandable approach that enhances and expands the statistical toolset for readers. This book includes: New coverage of the sign test and the Kolmogorov-Smirnov two-sample test in an effort to offer a logical and natural progression to statistical powerSPSS® (Version 21) software and updated screen ca
Categorical and nonparametric data analysis choosing the best statistical technique
Nussbaum, E Michael
2014-01-01
Featuring in-depth coverage of categorical and nonparametric statistics, this book provides a conceptual framework for choosing the most appropriate type of test in various research scenarios. Class tested at the University of Nevada, the book's clear explanations of the underlying assumptions, computer simulations, and Exploring the Concept boxes help reduce reader anxiety. Problems inspired by actual studies provide meaningful illustrations of the techniques. The underlying assumptions of each test and the factors that impact validity and statistical power are reviewed so readers can explain
Nonparametric statistical structuring of knowledge systems using binary feature matches
DEFF Research Database (Denmark)
Mørup, Morten; Glückstad, Fumiko Kano; Herlau, Tue
2014-01-01
statistical support and how this approach generalizes to the structuring and alignment of knowledge systems. We propose a non-parametric Bayesian generative model for structuring binary feature data that does not depend on a specific choice of similarity measure. We jointly model all combinations of binary......Structuring knowledge systems with binary features is often based on imposing a similarity measure and clustering objects according to this similarity. Unfortunately, such analyses can be heavily influenced by the choice of similarity measure. Furthermore, it is unclear at which level clusters have...
Testing for a constant coefficient of variation in nonparametric regression
Dette, Holger; Marchlewski, Mareen; Wagener, Jens
2010-01-01
In the common nonparametric regression model Y_i=m(X_i)+sigma(X_i)epsilon_i we consider the problem of testing the hypothesis that the coefficient of the scale and location function is constant. The test is based on a comparison of the observations Y_i=\\hat{sigma}(X_i) with their mean by a smoothed empirical process, where \\hat{sigma} denotes the local linear estimate of the scale function. We show weak convergence of a centered version of this process to a Gaussian process under the null ...
Generative Temporal Modelling of Neuroimaging - Decomposition and Nonparametric Testing
DEFF Research Database (Denmark)
Hald, Ditte Høvenhoff
The goal of this thesis is to explore two improvements for functional magnetic resonance imaging (fMRI) analysis; namely our proposed decomposition method and an extension to the non-parametric testing framework. Analysis of fMRI allows researchers to investigate the functional processes...... of the brain, and provides insight into neuronal coupling during mental processes or tasks. The decomposition method is a Gaussian process-based independent components analysis (GPICA), which incorporates a temporal dependency in the sources. A hierarchical model specification is used, featuring both...
Laboratory-Tutorial activities for teaching probability
Wittmann, M C; Morgan, J T; Feeley, Roger E.; Morgan, Jeffrey T.; Wittmann, Michael C.
2006-01-01
We report on the development of students' ideas of probability and probability density in a University of Maine laboratory-based general education physics course called Intuitive Quantum Physics. Students in the course are generally math phobic with unfavorable expectations about the nature of physics and their ability to do it. We describe a set of activities used to teach concepts of probability and probability density. Rudimentary knowledge of mechanics is needed for one activity, but otherwise the material requires no additional preparation. Extensions of the activities include relating probability density to potential energy graphs for certain "touchstone" examples. Students have difficulties learning the target concepts, such as comparing the ratio of time in a region to total time in all regions. Instead, they often focus on edge effects, pattern match to previously studied situations, reason about necessary but incomplete macroscopic elements of the system, use the gambler's fallacy, and use expectati...
Edwards, William F.; Shiflett, Ray C.; Shultz, Harris
2008-01-01
The mathematical model used to describe independence between two events in probability has a non-intuitive consequence called dependent spaces. The paper begins with a very brief history of the development of probability, then defines dependent spaces, and reviews what is known about finite spaces with uniform probability. The study of finite…
Benci, Vieri; Horsten, Leon; Wenmackers, Sylvia
We propose an alternative approach to probability theory closely related to the framework of numerosity theory: non-Archimedean probability (NAP). In our approach, unlike in classical probability theory, all subsets of an infinite sample space are measurable and only the empty set gets assigned
Interpretations of probability
Khrennikov, Andrei
2009-01-01
This is the first fundamental book devoted to non-Kolmogorov probability models. It provides a mathematical theory of negative probabilities, with numerous applications to quantum physics, information theory, complexity, biology and psychology. The book also presents an interesting model of cognitive information reality with flows of information probabilities, describing the process of thinking, social, and psychological phenomena.
Benci, Vieri; Horsten, Leon; Wenmackers, Sylvia
2013-01-01
We propose an alternative approach to probability theory closely related to the framework of numerosity theory: non-Archimedean probability (NAP). In our approach, unlike in classical probability theory, all subsets of an infinite sample space are measurable and only the empty set gets assigned prob
Xu, Yonghong; Gao, Xiaohuan; Wang, Zhengxi
2014-04-01
Missing data represent a general problem in many scientific fields, especially in medical survival analysis. Dealing with censored data, interpolation method is one of important methods. However, most of the interpolation methods replace the censored data with the exact data, which will distort the real distribution of the censored data and reduce the probability of the real data falling into the interpolation data. In order to solve this problem, we in this paper propose a nonparametric method of estimating the survival function of right-censored and interval-censored data and compare its performance to SC (self-consistent) algorithm. Comparing to the average interpolation and the nearest neighbor interpolation method, the proposed method in this paper replaces the right-censored data with the interval-censored data, and greatly improves the probability of the real data falling into imputation interval. Then it bases on the empirical distribution theory to estimate the survival function of right-censored and interval-censored data. The results of numerical examples and a real breast cancer data set demonstrated that the proposed method had higher accuracy and better robustness for the different proportion of the censored data. This paper provides a good method to compare the clinical treatments performance with estimation of the survival data of the patients. This pro vides some help to the medical survival data analysis.
Nonparametric Problem-Space Clustering: Learning Efficient Codes for Cognitive Control Tasks
Directory of Open Access Journals (Sweden)
Domenico Maisto
2016-02-01
Full Text Available We present an information-theoretic method permitting one to find structure in a problem space (here, in a spatial navigation domain and cluster it in ways that are convenient to solve different classes of control problems, which include planning a path to a goal from a known or an unknown location, achieving multiple goals and exploring a novel environment. Our generative nonparametric approach, called the generative embedded Chinese restaurant process (geCRP, extends the family of Chinese restaurant process (CRP models by introducing a parameterizable notion of distance (or kernel between the states to be clustered together. By using different kernels, such as the the conditional probability or joint probability of two states, the same geCRP method clusters the environment in ways that are more sensitive to different control-related information, such as goal, sub-goal and path information. We perform a series of simulations in three scenarios—an open space, a grid world with four rooms and a maze having the same structure as the Hanoi Tower—in order to illustrate the characteristics of the different clusters (obtained using different kernels and their relative benefits for solving planning and control problems.
Non-Parametric Evolutionary Algorithm for Estimating Root Zone Soil Moisture
Mohanty, B.; Shin, Y.; Ines, A. M.
2013-12-01
Prediction of root zone soil moisture is critical for water resources management. In this study, we explored a non-parametric evolutionary algorithm for estimating root zone soil moisture from a time series of spatially-distributed rainfall across multiple weather locations under two different hydro-climatic regions. A new genetic algorithm-based hidden Markov model (HMMGA) was developed to estimate long-term root zone soil moisture dynamics at different soil depths. Also, we analyzed rainfall occurrence probabilities and dry/wet spell lengths reproduced by this approach. The HMMGA was used to estimate the optimal state sequences (weather states) based on the precipitation history. Historical root zone soil moisture statistics were then determined based on the weather state conditions. To test the new approach, we selected two different soil moisture fields, Oklahoma (130 km x 130 km) and Illinois (300 km x 500 km), during 1995 to 2009 and 1994 to 2010, respectively. We found that the newly developed framework performed well in predicting root zone soil moisture dynamics at both the spatial scales. Also, the reproduced rainfall occurrence probabilities and dry/wet spell lengths matched well with the observations at the spatio-temporal scales. Since the proposed algorithm requires only precipitation and historical soil moisture data from existing, established weather stations, it can serve an attractive alternative for predicting root zone soil moisture in the future using climate change scenarios and root zone soil moisture history.
Dynamical Simulation of Probabilities
Zak, Michail
1996-01-01
It has been demonstrated that classical probabilities, and in particular, probabilistic Turing machine, can be simulated by combining chaos and non-Lipschitz dynamics, without utilization of any man-made devices(such as random number generators). Self-orgainizing properties of systems coupling simulated and calculated probabilities and their link to quantum computations are discussed. Special attention was focused upon coupled stochastic processes, defined in terms of conditional probabilities, for which joint probability does not exist. Simulations of quantum probabilities are also discussed.
Childers, Timothy
2013-01-01
Probability is increasingly important for our understanding of the world. What is probability? How do we model it, and how do we use it? Timothy Childers presents a lively introduction to the foundations of probability and to philosophical issues it raises. He keeps technicalities to a minimum, and assumes no prior knowledge of the subject. He explains the main interpretations of probability-frequentist, propensity, classical, Bayesian, and objective Bayesian-and uses stimulatingexamples to bring the subject to life. All students of philosophy will benefit from an understanding of probability,
1st Conference of the International Society for Nonparametric Statistics
Lahiri, S; Politis, Dimitris
2014-01-01
This volume is composed of peer-reviewed papers that have developed from the First Conference of the International Society for NonParametric Statistics (ISNPS). This inaugural conference took place in Chalkidiki, Greece, June 15-19, 2012. It was organized with the co-sponsorship of the IMS, the ISI, and other organizations. M.G. Akritas, S.N. Lahiri, and D.N. Politis are the first executive committee members of ISNPS, and the editors of this volume. ISNPS has a distinguished Advisory Committee that includes Professors R.Beran, P.Bickel, R. Carroll, D. Cook, P. Hall, R. Johnson, B. Lindsay, E. Parzen, P. Robinson, M. Rosenblatt, G. Roussas, T. SubbaRao, and G. Wahba. The Charting Committee of ISNPS consists of more than 50 prominent researchers from all over the world. The chapters in this volume bring forth recent advances and trends in several areas of nonparametric statistics. In this way, the volume facilitates the exchange of research ideas, promotes collaboration among researchers from all over the wo...
Non-parametric Morphologies of Mergers in the Illustris Simulation
Bignone, Lucas A; Sillero, Emanuel; Pedrosa, Susana E; Pellizza, Leonardo J; Lambas, Diego G
2016-01-01
We study non-parametric morphologies of mergers events in a cosmological context, using the Illustris project. We produce mock g-band images comparable to observational surveys from the publicly available Illustris simulation idealized mock images at $z=0$. We then measure non parametric indicators: asymmetry, Gini, $M_{20}$, clumpiness and concentration for a set of galaxies with $M_* >10^{10}$ M$_\\odot$. We correlate these automatic statistics with the recent merger history of galaxies and with the presence of close companions. Our main contribution is to assess in a cosmological framework, the empirically derived non-parametric demarcation line and average time-scales used to determine the merger rate observationally. We found that 98 per cent of galaxies above the demarcation line have a close companion or have experienced a recent merger event. On average, merger signatures obtained from the $G-M_{20}$ criteria anticorrelate clearly with the elapsing time to the last merger event. We also find that the a...
Genomic breeding value estimation using nonparametric additive regression models
Directory of Open Access Journals (Sweden)
Solberg Trygve
2009-01-01
Full Text Available Abstract Genomic selection refers to the use of genomewide dense markers for breeding value estimation and subsequently for selection. The main challenge of genomic breeding value estimation is the estimation of many effects from a limited number of observations. Bayesian methods have been proposed to successfully cope with these challenges. As an alternative class of models, non- and semiparametric models were recently introduced. The present study investigated the ability of nonparametric additive regression models to predict genomic breeding values. The genotypes were modelled for each marker or pair of flanking markers (i.e. the predictors separately. The nonparametric functions for the predictors were estimated simultaneously using additive model theory, applying a binomial kernel. The optimal degree of smoothing was determined by bootstrapping. A mutation-drift-balance simulation was carried out. The breeding values of the last generation (genotyped was predicted using data from the next last generation (genotyped and phenotyped. The results show moderate to high accuracies of the predicted breeding values. A determination of predictor specific degree of smoothing increased the accuracy.
Nonparametric Analyses of Log-Periodic Precursors to Financial Crashes
Zhou, Wei-Xing; Sornette, Didier
We apply two nonparametric methods to further test the hypothesis that log-periodicity characterizes the detrended price trajectory of large financial indices prior to financial crashes or strong corrections. The term "parametric" refers here to the use of the log-periodic power law formula to fit the data; in contrast, "nonparametric" refers to the use of general tools such as Fourier transform, and in the present case the Hilbert transform and the so-called (H, q)-analysis. The analysis using the (H, q)-derivative is applied to seven time series ending with the October 1987 crash, the October 1997 correction and the April 2000 crash of the Dow Jones Industrial Average (DJIA), the Standard & Poor 500 and Nasdaq indices. The Hilbert transform is applied to two detrended price time series in terms of the ln(tc-t) variable, where tc is the time of the crash. Taking all results together, we find strong evidence for a universal fundamental log-frequency f=1.02±0.05 corresponding to the scaling ratio λ=2.67±0.12. These values are in very good agreement with those obtained in earlier works with different parametric techniques. This note is extracted from a long unpublished report with 58 figures available at , which extensively describes the evidence we have accumulated on these seven time series, in particular by presenting all relevant details so that the reader can judge for himself or herself the validity and robustness of the results.
Stochastic Earthquake Rupture Modeling Using Nonparametric Co-Regionalization
Lee, Kyungbook; Song, Seok Goo
2016-10-01
Accurate predictions of the intensity and variability of ground motions are essential in simulation-based seismic hazard assessment. Advanced simulation-based ground motion prediction methods have been proposed to complement the empirical approach, which suffers from the lack of observed ground motion data, especially in the near-source region for large events. It is important to quantify the variability of the earthquake rupture process for future events and to produce a number of rupture scenario models to capture the variability in simulation-based ground motion predictions. In this study, we improved the previously developed stochastic earthquake rupture modeling method by applying the nonparametric co-regionalization, which was proposed in geostatistics, to the correlation models estimated from dynamically derived earthquake rupture models. The nonparametric approach adopted in this study is computationally efficient and, therefore, enables us to simulate numerous rupture scenarios, including large events (M > 7.0). It also gives us an opportunity to check the shape of true input correlation models in stochastic modeling after being deformed for permissibility. We expect that this type of modeling will improve our ability to simulate a wide range of rupture scenario models and thereby predict ground motions and perform seismic hazard assessment more accurately.
A non-parametric framework for estimating threshold limit values
Directory of Open Access Journals (Sweden)
Ulm Kurt
2005-11-01
Full Text Available Abstract Background To estimate a threshold limit value for a compound known to have harmful health effects, an 'elbow' threshold model is usually applied. We are interested on non-parametric flexible alternatives. Methods We describe how a step function model fitted by isotonic regression can be used to estimate threshold limit values. This method returns a set of candidate locations, and we discuss two algorithms to select the threshold among them: the reduced isotonic regression and an algorithm considering the closed family of hypotheses. We assess the performance of these two alternative approaches under different scenarios in a simulation study. We illustrate the framework by analysing the data from a study conducted by the German Research Foundation aiming to set a threshold limit value in the exposure to total dust at workplace, as a causal agent for developing chronic bronchitis. Results In the paper we demonstrate the use and the properties of the proposed methodology along with the results from an application. The method appears to detect the threshold with satisfactory success. However, its performance can be compromised by the low power to reject the constant risk assumption when the true dose-response relationship is weak. Conclusion The estimation of thresholds based on isotonic framework is conceptually simple and sufficiently powerful. Given that in threshold value estimation context there is not a gold standard method, the proposed model provides a useful non-parametric alternative to the standard approaches and can corroborate or challenge their findings.
Using non-parametric methods in econometric production analysis
DEFF Research Database (Denmark)
Czekaj, Tomasz Gerard; Henningsen, Arne
2012-01-01
Econometric estimation of production functions is one of the most common methods in applied economic production analysis. These studies usually apply parametric estimation techniques, which obligate the researcher to specify a functional form of the production function of which the Cobb-Douglas a......Econometric estimation of production functions is one of the most common methods in applied economic production analysis. These studies usually apply parametric estimation techniques, which obligate the researcher to specify a functional form of the production function of which the Cobb...... parameter estimates, but also in biased measures which are derived from the parameters, such as elasticities. Therefore, we propose to use non-parametric econometric methods. First, these can be applied to verify the functional form used in parametric production analysis. Second, they can be directly used...... to estimate production functions without the specification of a functional form. Therefore, they avoid possible misspecification errors due to the use of an unsuitable functional form. In this paper, we use parametric and non-parametric methods to identify the optimal size of Polish crop farms...
Bayesian nonparametric centered random effects models with variable selection.
Yang, Mingan
2013-03-01
In a linear mixed effects model, it is common practice to assume that the random effects follow a parametric distribution such as a normal distribution with mean zero. However, in the case of variable selection, substantial violation of the normality assumption can potentially impact the subset selection and result in poor interpretation and even incorrect results. In nonparametric random effects models, the random effects generally have a nonzero mean, which causes an identifiability problem for the fixed effects that are paired with the random effects. In this article, we focus on a Bayesian method for variable selection. We characterize the subject-specific random effects nonparametrically with a Dirichlet process and resolve the bias simultaneously. In particular, we propose flexible modeling of the conditional distribution of the random effects with changes across the predictor space. The approach is implemented using a stochastic search Gibbs sampler to identify subsets of fixed effects and random effects to be included in the model. Simulations are provided to evaluate and compare the performance of our approach to the existing ones. We then apply the new approach to a real data example, cross-country and interlaboratory rodent uterotrophic bioassay.
Wavelet Estimators in Nonparametric Regression: A Comparative Simulation Study
Directory of Open Access Journals (Sweden)
Anestis Antoniadis
2001-06-01
Full Text Available Wavelet analysis has been found to be a powerful tool for the nonparametric estimation of spatially-variable objects. We discuss in detail wavelet methods in nonparametric regression, where the data are modelled as observations of a signal contaminated with additive Gaussian noise, and provide an extensive review of the vast literature of wavelet shrinkage and wavelet thresholding estimators developed to denoise such data. These estimators arise from a wide range of classical and empirical Bayes methods treating either individual or blocks of wavelet coefficients. We compare various estimators in an extensive simulation study on a variety of sample sizes, test functions, signal-to-noise ratios and wavelet filters. Because there is no single criterion that can adequately summarise the behaviour of an estimator, we use various criteria to measure performance in finite sample situations. Insight into the performance of these estimators is obtained from graphical outputs and numerical tables. In order to provide some hints of how these estimators should be used to analyse real data sets, a detailed practical step-by-step illustration of a wavelet denoising analysis on electrical consumption is provided. Matlab codes are provided so that all figures and tables in this paper can be reproduced.
Computing Economies of Scope Using Robust Partial Frontier Nonparametric Methods
Directory of Open Access Journals (Sweden)
Pedro Carvalho
2016-03-01
Full Text Available This paper proposes a methodology to examine economies of scope using the recent order-α nonparametric method. It allows us to investigate economies of scope by comparing the efficient order-α frontiers of firms that produce two or more goods with the efficient order-α frontiers of firms that produce only one good. To accomplish this, and because the order-α frontiers are irregular, we suggest to linearize them by the DEA estimator. The proposed methodology uses partial frontier nonparametric methods that are more robust than the traditional full frontier methods. By using a sample of 67 Portuguese water utilities for the period 2002–2008 and, also, a simulated sample, we prove the usefulness of the approach adopted and show that if only the full frontier methods were used, they would lead to different results. We found evidence of economies of scope in the provision of water supply and wastewater services simultaneously by water utilities in Portugal.
Bayesian nonparametric dictionary learning for compressed sensing MRI.
Huang, Yue; Paisley, John; Lin, Qin; Ding, Xinghao; Fu, Xueyang; Zhang, Xiao-Ping
2014-12-01
We develop a Bayesian nonparametric model for reconstructing magnetic resonance images (MRIs) from highly undersampled k -space data. We perform dictionary learning as part of the image reconstruction process. To this end, we use the beta process as a nonparametric dictionary learning prior for representing an image patch as a sparse combination of dictionary elements. The size of the dictionary and patch-specific sparsity pattern are inferred from the data, in addition to other dictionary learning variables. Dictionary learning is performed directly on the compressed image, and so is tailored to the MRI being considered. In addition, we investigate a total variation penalty term in combination with the dictionary learning model, and show how the denoising property of dictionary learning removes dependence on regularization parameters in the noisy setting. We derive a stochastic optimization algorithm based on Markov chain Monte Carlo for the Bayesian model, and use the alternating direction method of multipliers for efficiently performing total variation minimization. We present empirical results on several MRI, which show that the proposed regularization framework can improve reconstruction accuracy over other methods.
Non-parametric Deprojection of Surface Brightness Profiles of Galaxies in Generalised Geometries
Chakrabarty, Dalia
2009-01-01
We present a new Bayesian non-parametric deprojection algorithm DOPING (Deprojection of Observed Photometry using and INverse Gambit), that is designed to extract 3-D luminosity density distributions $\\rho$ from observed surface brightness maps $I$, in generalised geometries, while taking into account changes in intrinsic shape with radius, using a penalised likelihood approach and an MCMC optimiser. We provide the most likely solution to the integral equation that represents deprojection of the measured $I$ to $\\rho$. In order to keep the solution modular, we choose to express $\\rho$ as a function of the line-of-sight (LOS) coordinate $z$. We calculate the extent of the system along the ${\\bf z}$-axis, for a given point on the image that lies within an identified isophotal annulus. The extent along the LOS is binned and density is held a constant over each such $z$-bin. The code begins with a seed density and at the beginning of an iterative step, the trial $\\rho$ is updated. Comparison of the projection of ...
Spectral decompositions of multiple time series: a Bayesian non-parametric approach.
Macaro, Christian; Prado, Raquel
2014-01-01
We consider spectral decompositions of multiple time series that arise in studies where the interest lies in assessing the influence of two or more factors. We write the spectral density of each time series as a sum of the spectral densities associated to the different levels of the factors. We then use Whittle's approximation to the likelihood function and follow a Bayesian non-parametric approach to obtain posterior inference on the spectral densities based on Bernstein-Dirichlet prior distributions. The prior is strategically important as it carries identifiability conditions for the models and allows us to quantify our degree of confidence in such conditions. A Markov chain Monte Carlo (MCMC) algorithm for posterior inference within this class of frequency-domain models is presented.We illustrate the approach by analyzing simulated and real data via spectral one-way and two-way models. In particular, we present an analysis of functional magnetic resonance imaging (fMRI) brain responses measured in individuals who participated in a designed experiment to study pain perception in humans.
DEFF Research Database (Denmark)
Effraimidis, Georgios; Dahl, Christian Møller
In this paper, we develop a fully nonparametric approach for the estimation of the cumulative incidence function with Missing At Random right-censored competing risks data. We obtain results on the pointwise asymptotic normality as well as the uniform convergence rate of the proposed nonparametric...... estimator. A simulation study that serves two purposes is provided. First, it illustrates in details how to implement our proposed nonparametric estimator. Secondly, it facilitates a comparison of the nonparametric estimator to a parametric counterpart based on the estimator of Lu and Liang (2008...
Determining the Mass of Kepler-78b with Nonparametric Gaussian Process Estimation
Grunblatt, Samuel Kai; Howard, Andrew; Haywood, Raphaëlle
2016-01-01
Kepler-78b is a transiting planet that is 1.2 times the radius of Earth and orbits a young, active K dwarf every 8 hr. The mass of Kepler-78b has been independently reported by two teams based on radial velocity (RV) measurements using the HIRES and HARPS-N spectrographs. Due to the active nature of the host star, a stellar activity model is required to distinguish and isolate the planetary signal in RV data. Whereas previous studies tested parametric stellar activity models, we modeled this system using nonparametric Gaussian process (GP) regression. We produced a GP regression of relevant Kepler photometry. We then use the posterior parameter distribution for our photometric fit as a prior for our simultaneous GP + Keplerian orbit models of the RV data sets. We tested three simple kernel functions for our GP regressions. Based on a Bayesian likelihood analysis, we selected a quasi-periodic kernel model with GP hyperparameters coupled between the two RV data sets, giving a Doppler amplitude of 1.86 ± 0.25 m s-1 and supporting our belief that the correlated noise we are modeling is astrophysical. The corresponding mass of 1.87-0.26+0.27 ME is consistent with that measured in previous studies, and more robust due to our nonparametric signal estimation. Based on our mass and the radius measurement from transit photometry, Kepler-78b has a bulk density of 6.0-1.4+1.9 g cm-3. We estimate that Kepler-78b is 32% ± 26% iron using a two-component rock-iron model. This is consistent with an Earth-like composition, with uncertainty spanning Moon-like to Mercury-like compositions.
Forecasting turbulent modes with nonparametric diffusion models: Learning from noisy data
Berry, Tyrus; Harlim, John
2016-04-01
In this paper, we apply a recently developed nonparametric modeling approach, the "diffusion forecast", to predict the time-evolution of Fourier modes of turbulent dynamical systems. While the diffusion forecasting method assumes the availability of a noise-free training data set observing the full state space of the dynamics, in real applications we often have only partial observations which are corrupted by noise. To alleviate these practical issues, following the theory of embedology, the diffusion model is built using the delay-embedding coordinates of the data. We show that this delay embedding biases the geometry of the data in a way which extracts the most stable component of the dynamics and reduces the influence of independent additive observation noise. The resulting diffusion forecast model approximates the semigroup solutions of the generator of the underlying dynamics in the limit of large data and when the observation noise vanishes. As in any standard forecasting problem, the forecasting skill depends crucially on the accuracy of the initial conditions. We introduce a novel Bayesian method for filtering the discrete-time noisy observations which works with the diffusion forecast to determine the forecast initial densities. Numerically, we compare this nonparametric approach with standard stochastic parametric models on a wide-range of well-studied turbulent modes, including the Lorenz-96 model in weakly chaotic to fully turbulent regimes and the barotropic modes of a quasi-geostrophic model with baroclinic instabilities. We show that when the only available data is the low-dimensional set of noisy modes that are being modeled, the diffusion forecast is indeed competitive to the perfect model.
Varying kernel density estimation on ℝ+
Mnatsakanov, Robert; Sarkisian, Khachatur
2015-01-01
In this article a new nonparametric density estimator based on the sequence of asymmetric kernels is proposed. This method is natural when estimating an unknown density function of a positive random variable. The rates of Mean Squared Error, Mean Integrated Squared Error, and the L1-consistency are investigated. Simulation studies are conducted to compare a new estimator and its modified version with traditional kernel density construction. PMID:26740729
Probability and radical behaviorism
Espinosa, James M.
1992-01-01
The concept of probability appears to be very important in the radical behaviorism of Skinner. Yet, it seems that this probability has not been accurately defined and is still ambiguous. I give a strict, relative frequency interpretation of probability and its applicability to the data from the science of behavior as supplied by cumulative records. Two examples of stochastic processes are given that may model the data from cumulative records that result under conditions of continuous reinforcement and extinction, respectively. PMID:22478114
Probability and radical behaviorism
Espinosa, James M.
1992-01-01
The concept of probability appears to be very important in the radical behaviorism of Skinner. Yet, it seems that this probability has not been accurately defined and is still ambiguous. I give a strict, relative frequency interpretation of probability and its applicability to the data from the science of behavior as supplied by cumulative records. Two examples of stochastic processes are given that may model the data from cumulative records that result under conditions of continuous reinforc...
STATISTICAL ANALYSIS, REPORTS), (*PROBABILITY, REPORTS), INFORMATION THEORY, DIFFERENTIAL EQUATIONS, STATISTICAL PROCESSES, STOCHASTIC PROCESSES, MULTIVARIATE ANALYSIS, DISTRIBUTION THEORY , DECISION THEORY, MEASURE THEORY, OPTIMIZATION
Ash, Robert B; Lukacs, E
1972-01-01
Real Analysis and Probability provides the background in real analysis needed for the study of probability. Topics covered range from measure and integration theory to functional analysis and basic concepts of probability. The interplay between measure theory and topology is also discussed, along with conditional probability and expectation, the central limit theorem, and strong laws of large numbers with respect to martingale theory.Comprised of eight chapters, this volume begins with an overview of the basic concepts of the theory of measure and integration, followed by a presentation of var
Florescu, Ionut
2013-01-01
THE COMPLETE COLLECTION NECESSARY FOR A CONCRETE UNDERSTANDING OF PROBABILITY Written in a clear, accessible, and comprehensive manner, the Handbook of Probability presents the fundamentals of probability with an emphasis on the balance of theory, application, and methodology. Utilizing basic examples throughout, the handbook expertly transitions between concepts and practice to allow readers an inclusive introduction to the field of probability. The book provides a useful format with self-contained chapters, allowing the reader easy and quick reference. Each chapter includes an introductio
Structuring feature space: a non-parametric method for volumetric transfer function generation.
Maciejewski, Ross; Woo, Insoo; Chen, Wei; Ebert, David S
2009-01-01
The use of multi-dimensional transfer functions for direct volume rendering has been shown to be an effective means of extracting materials and their boundaries for both scalar and multivariate data. The most common multi-dimensional transfer function consists of a two-dimensional (2D) histogram with axes representing a subset of the feature space (e.g., value vs. value gradient magnitude), with each entry in the 2D histogram being the number of voxels at a given feature space pair. Users then assign color and opacity to the voxel distributions within the given feature space through the use of interactive widgets (e.g., box, circular, triangular selection). Unfortunately, such tools lead users through a trial-and-error approach as they assess which data values within the feature space map to a given area of interest within the volumetric space. In this work, we propose the addition of non-parametric clustering within the transfer function feature space in order to extract patterns and guide transfer function generation. We apply a non-parametric kernel density estimation to group voxels of similar features within the 2D histogram. These groups are then binned and colored based on their estimated density, and the user may interactively grow and shrink the binned regions to explore feature boundaries and extract regions of interest. We also extend this scheme to temporal volumetric data in which time steps of 2D histograms are composited into a histogram volume. A three-dimensional (3D) density estimation is then applied, and users can explore regions within the feature space across time without adjusting the transfer function at each time step. Our work enables users to effectively explore the structures found within a feature space of the volume and provide a context in which the user can understand how these structures relate to their volumetric data. We provide tools for enhanced exploration and manipulation of the transfer function, and we show that the initial
On Quantum Conditional Probability
Directory of Open Access Journals (Sweden)
Isabel Guerra Bobo
2013-02-01
Full Text Available We argue that quantum theory does not allow for a generalization of the notion of classical conditional probability by showing that the probability defined by the Lüders rule, standardly interpreted in the literature as the quantum-mechanical conditionalization rule, cannot be interpreted as such.
Choice Probability Generating Functions
DEFF Research Database (Denmark)
Fosgerau, Mogens; McFadden, Daniel L; Bierlaire, Michel
This paper considers discrete choice, with choice probabilities coming from maximization of preferences from a random utility field perturbed by additive location shifters (ARUM). Any ARUM can be characterized by a choice-probability generating function (CPGF) whose gradient gives the choice...
Freund, John E
1993-01-01
Thorough, lucid coverage of permutations and factorials, probabilities and odds, frequency interpretation, mathematical expectation, decision making, postulates of probability, rule of elimination, binomial distribution, geometric distribution, standard deviation, law of large numbers, and much more. Exercises with some solutions. Summary. Bibliography. Includes 42 black-and-white illustrations. 1973 edition.
Choice Probability Generating Functions
DEFF Research Database (Denmark)
Fosgerau, Mogens; McFadden, Daniel L; Bierlaire, Michel
This paper considers discrete choice, with choice probabilities coming from maximization of preferences from a random utility field perturbed by additive location shifters (ARUM). Any ARUM can be characterized by a choice-probability generating function (CPGF) whose gradient gives the choice...
Choice probability generating functions
DEFF Research Database (Denmark)
Fosgerau, Mogens; McFadden, Daniel; Bierlaire, Michel
2013-01-01
This paper considers discrete choice, with choice probabilities coming from maximization of preferences from a random utility field perturbed by additive location shifters (ARUM). Any ARUM can be characterized by a choice-probability generating function (CPGF) whose gradient gives the choice...
Probability, Nondeterminism and Concurrency
DEFF Research Database (Denmark)
Varacca, Daniele
Nondeterminism is modelled in domain theory by the notion of a powerdomain, while probability is modelled by that of the probabilistic powerdomain. Some problems arise when we want to combine them in order to model computation in which both nondeterminism and probability are present. In particula...
Robust Depth-Weighted Wavelet for Nonparametric Regression Models
Institute of Scientific and Technical Information of China (English)
Lu LIN
2005-01-01
In the nonpaxametric regression models, the original regression estimators including kernel estimator, Fourier series estimator and wavelet estimator are always constructed by the weighted sum of data, and the weights depend only on the distance between the design points and estimation points. As a result these estimators are not robust to the perturbations in data. In order to avoid this problem, a new nonparametric regression model, called the depth-weighted regression model, is introduced and then the depth-weighted wavelet estimation is defined. The new estimation is robust to the perturbations in data, which attains very high breakdown value close to 1/2. On the other hand, some asymptotic behaviours such as asymptotic normality are obtained. Some simulations illustrate that the proposed wavelet estimator is more robust than the original wavelet estimator and, as a price to pay for the robustness, the new method is slightly less efficient than the original method.
Nonparametric Bayesian inference of the microcanonical stochastic block model
Peixoto, Tiago P
2016-01-01
A principled approach to characterize the hidden modular structure of networks is to formulate generative models, and then infer their parameters from data. When the desired structure is composed of modules or "communities", a suitable choice for this task is the stochastic block model (SBM), where nodes are divided into groups, and the placement of edges is conditioned on the group memberships. Here, we present a nonparametric Bayesian method to infer the modular structure of empirical networks, including the number of modules and their hierarchical organization. We focus on a microcanonical variant of the SBM, where the structure is imposed via hard constraints. We show how this simple model variation allows simultaneously for two important improvements over more traditional inference approaches: 1. Deeper Bayesian hierarchies, with noninformative priors replaced by sequences of priors and hyperpriors, that not only remove limitations that seriously degrade the inference on large networks, but also reveal s...
A Non-Parametric Spatial Independence Test Using Symbolic Entropy
Directory of Open Access Journals (Sweden)
López Hernández, Fernando
2008-01-01
Full Text Available In the present paper, we construct a new, simple, consistent and powerful test forspatial independence, called the SG test, by using symbolic dynamics and symbolic entropyas a measure of spatial dependence. We also give a standard asymptotic distribution of anaffine transformation of the symbolic entropy under the null hypothesis of independencein the spatial process. The test statistic and its standard limit distribution, with theproposed symbolization, are invariant to any monotonuous transformation of the data.The test applies to discrete or continuous distributions. Given that the test is based onentropy measures, it avoids smoothed nonparametric estimation. We include a MonteCarlo study of our test, together with the well-known Moran’s I, the SBDS (de Graaffet al, 2001 and (Brett and Pinkse, 1997 non parametric test, in order to illustrate ourapproach.
Analyzing single-molecule time series via nonparametric Bayesian inference.
Hines, Keegan E; Bankston, John R; Aldrich, Richard W
2015-02-03
The ability to measure the properties of proteins at the single-molecule level offers an unparalleled glimpse into biological systems at the molecular scale. The interpretation of single-molecule time series has often been rooted in statistical mechanics and the theory of Markov processes. While existing analysis methods have been useful, they are not without significant limitations including problems of model selection and parameter nonidentifiability. To address these challenges, we introduce the use of nonparametric Bayesian inference for the analysis of single-molecule time series. These methods provide a flexible way to extract structure from data instead of assuming models beforehand. We demonstrate these methods with applications to several diverse settings in single-molecule biophysics. This approach provides a well-constrained and rigorously grounded method for determining the number of biophysical states underlying single-molecule data. Copyright © 2015 Biophysical Society. Published by Elsevier Inc. All rights reserved.
Analyzing multiple spike trains with nonparametric Granger causality.
Nedungadi, Aatira G; Rangarajan, Govindan; Jain, Neeraj; Ding, Mingzhou
2009-08-01
Simultaneous recordings of spike trains from multiple single neurons are becoming commonplace. Understanding the interaction patterns among these spike trains remains a key research area. A question of interest is the evaluation of information flow between neurons through the analysis of whether one spike train exerts causal influence on another. For continuous-valued time series data, Granger causality has proven an effective method for this purpose. However, the basis for Granger causality estimation is autoregressive data modeling, which is not directly applicable to spike trains. Various filtering options distort the properties of spike trains as point processes. Here we propose a new nonparametric approach to estimate Granger causality directly from the Fourier transforms of spike train data. We validate the method on synthetic spike trains generated by model networks of neurons with known connectivity patterns and then apply it to neurons simultaneously recorded from the thalamus and the primary somatosensory cortex of a squirrel monkey undergoing tactile stimulation.
Prior processes and their applications nonparametric Bayesian estimation
Phadia, Eswar G
2016-01-01
This book presents a systematic and comprehensive treatment of various prior processes that have been developed over the past four decades for dealing with Bayesian approach to solving selected nonparametric inference problems. This revised edition has been substantially expanded to reflect the current interest in this area. After an overview of different prior processes, it examines the now pre-eminent Dirichlet process and its variants including hierarchical processes, then addresses new processes such as dependent Dirichlet, local Dirichlet, time-varying and spatial processes, all of which exploit the countable mixture representation of the Dirichlet process. It subsequently discusses various neutral to right type processes, including gamma and extended gamma, beta and beta-Stacy processes, and then describes the Chinese Restaurant, Indian Buffet and infinite gamma-Poisson processes, which prove to be very useful in areas such as machine learning, information retrieval and featural modeling. Tailfree and P...
Using non-parametric methods in econometric production analysis
DEFF Research Database (Denmark)
Czekaj, Tomasz Gerard; Henningsen, Arne
Econometric estimation of production functions is one of the most common methods in applied economic production analysis. These studies usually apply parametric estimation techniques, which obligate the researcher to specify the functional form of the production function. Most often, the Cobb......-Douglas or the Translog production function is used. However, the specification of a functional form for the production function involves the risk of specifying a functional form that is not similar to the “true” relationship between the inputs and the output. This misspecification might result in biased estimation...... results—including measures that are of interest of applied economists, such as elasticities. Therefore, we propose to use nonparametric econometric methods. First, they can be applied to verify the functional form used in parametric estimations of production functions. Second, they can be directly used...
Nonparametric Estimation of Distributions in Random Effects Models
Hart, Jeffrey D.
2011-01-01
We propose using minimum distance to obtain nonparametric estimates of the distributions of components in random effects models. A main setting considered is equivalent to having a large number of small datasets whose locations, and perhaps scales, vary randomly, but which otherwise have a common distribution. Interest focuses on estimating the distribution that is common to all datasets, knowledge of which is crucial in multiple testing problems where a location/scale invariant test is applied to every small dataset. A detailed algorithm for computing minimum distance estimates is proposed, and the usefulness of our methodology is illustrated by a simulation study and an analysis of microarray data. Supplemental materials for the article, including R-code and a dataset, are available online. © 2011 American Statistical Association.
Curve registration by nonparametric goodness-of-fit testing
Dalalyan, Arnak
2011-01-01
The problem of curve registration appears in many different areas of applications ranging from neuroscience to road traffic modeling. In the present work, we propose a nonparametric testing framework in which we develop a generalized likelihood ratio test to perform curve registration. We first prove that, under the null hypothesis, the resulting test statistic is asymptotically distributed as a chi-squared random variable. This result, often referred to as Wilks' phenomenon, provides a natural threshold for the test of a prescribed asymptotic significance level and a natural measure of lack-of-fit in terms of the p-value of the chi squared test. We also prove that the proposed test is consistent, i.e., its power is asymptotically equal to 1. Some numerical experiments on synthetic datasets are reported as well.
Nonparametric Model of Smooth Muscle Force Production During Electrical Stimulation.
Cole, Marc; Eikenberry, Steffen; Kato, Takahide; Sandler, Roman A; Yamashiro, Stanley M; Marmarelis, Vasilis Z
2017-03-01
A nonparametric model of smooth muscle tension response to electrical stimulation was estimated using the Laguerre expansion technique of nonlinear system kernel estimation. The experimental data consisted of force responses of smooth muscle to energy-matched alternating single pulse and burst current stimuli. The burst stimuli led to at least a 10-fold increase in peak force in smooth muscle from Mytilus edulis, despite the constant energy constraint. A linear model did not fit the data. However, a second-order model fit the data accurately, so the higher-order models were not required to fit the data. Results showed that smooth muscle force response is not linearly related to the stimulation power.
Nonparametric estimation of stochastic differential equations with sparse Gaussian processes
García, Constantino A.; Otero, Abraham; Félix, Paulo; Presedo, Jesús; Márquez, David G.
2017-08-01
The application of stochastic differential equations (SDEs) to the analysis of temporal data has attracted increasing attention, due to their ability to describe complex dynamics with physically interpretable equations. In this paper, we introduce a nonparametric method for estimating the drift and diffusion terms of SDEs from a densely observed discrete time series. The use of Gaussian processes as priors permits working directly in a function-space view and thus the inference takes place directly in this space. To cope with the computational complexity that requires the use of Gaussian processes, a sparse Gaussian process approximation is provided. This approximation permits the efficient computation of predictions for the drift and diffusion terms by using a distribution over a small subset of pseudosamples. The proposed method has been validated using both simulated data and real data from economy and paleoclimatology. The application of the method to real data demonstrates its ability to capture the behavior of complex systems.
Indoor Positioning Using Nonparametric Belief Propagation Based on Spanning Trees
Directory of Open Access Journals (Sweden)
Savic Vladimir
2010-01-01
Full Text Available Nonparametric belief propagation (NBP is one of the best-known methods for cooperative localization in sensor networks. It is capable of providing information about location estimation with appropriate uncertainty and to accommodate non-Gaussian distance measurement errors. However, the accuracy of NBP is questionable in loopy networks. Therefore, in this paper, we propose a novel approach, NBP based on spanning trees (NBP-ST created by breadth first search (BFS method. In addition, we propose a reliable indoor model based on obtained measurements in our lab. According to our simulation results, NBP-ST performs better than NBP in terms of accuracy and communication cost in the networks with high connectivity (i.e., highly loopy networks. Furthermore, the computational and communication costs are nearly constant with respect to the transmission radius. However, the drawbacks of proposed method are a little bit higher computational cost and poor performance in low-connected networks.
Revealing components of the galaxy population through nonparametric techniques
Bamford, Steven P; Nichol, Robert C; Miller, Christopher J; Wasserman, Larry; Genovese, Christopher R; Freeman, Peter E
2008-01-01
The distributions of galaxy properties vary with environment, and are often multimodal, suggesting that the galaxy population may be a combination of multiple components. The behaviour of these components versus environment holds details about the processes of galaxy development. To release this information we apply a novel, nonparametric statistical technique, identifying four components present in the distribution of galaxy H$\\alpha$ emission-line equivalent-widths. We interpret these components as passive, star-forming, and two varieties of active galactic nuclei. Independent of this interpretation, the properties of each component are remarkably constant as a function of environment. Only their relative proportions display substantial variation. The galaxy population thus appears to comprise distinct components which are individually independent of environment, with galaxies rapidly transitioning between components as they move into denser environments.
Multi-Directional Non-Parametric Analysis of Agricultural Efficiency
DEFF Research Database (Denmark)
Balezentis, Tomas
This thesis seeks to develop methodologies for assessment of agricultural efficiency and employ them to Lithuanian family farms. In particular, we focus on three particular objectives throughout the research: (i) to perform a fully non-parametric analysis of efficiency effects, (ii) to extend...... relative to labour, intermediate consumption and land (in some cases land was not treated as a discretionary input). These findings call for further research on relationships among financial structure, investment decisions, and efficiency in Lithuanian family farms. Application of different techniques...... of stochasticity associated with Lithuanian family farm performance. The former technique showed that the farms differed in terms of the mean values and variance of the efficiency scores over time with some clear patterns prevailing throughout the whole research period. The fuzzy Free Disposal Hull showed...
Binary Classifier Calibration Using a Bayesian Non-Parametric Approach.
Naeini, Mahdi Pakdaman; Cooper, Gregory F; Hauskrecht, Milos
Learning probabilistic predictive models that are well calibrated is critical for many prediction and decision-making tasks in Data mining. This paper presents two new non-parametric methods for calibrating outputs of binary classification models: a method based on the Bayes optimal selection and a method based on the Bayesian model averaging. The advantage of these methods is that they are independent of the algorithm used to learn a predictive model, and they can be applied in a post-processing step, after the model is learned. This makes them applicable to a wide variety of machine learning models and methods. These calibration methods, as well as other methods, are tested on a variety of datasets in terms of both discrimination and calibration performance. The results show the methods either outperform or are comparable in performance to the state-of-the-art calibration methods.
Parametric or nonparametric? A parametricness index for model selection
Liu, Wei; 10.1214/11-AOS899
2012-01-01
In model selection literature, two classes of criteria perform well asymptotically in different situations: Bayesian information criterion (BIC) (as a representative) is consistent in selection when the true model is finite dimensional (parametric scenario); Akaike's information criterion (AIC) performs well in an asymptotic efficiency when the true model is infinite dimensional (nonparametric scenario). But there is little work that addresses if it is possible and how to detect the situation that a specific model selection problem is in. In this work, we differentiate the two scenarios theoretically under some conditions. We develop a measure, parametricness index (PI), to assess whether a model selected by a potentially consistent procedure can be practically treated as the true model, which also hints on AIC or BIC is better suited for the data for the goal of estimating the regression function. A consequence is that by switching between AIC and BIC based on the PI, the resulting regression estimator is si...
Nonparametric reconstruction of the Om diagnostic to test LCDM
Escamilla-Rivera, Celia
2015-01-01
Cosmic acceleration is usually related with the unknown dark energy, which equation of state, w(z), is constrained and numerically confronted with independent astrophysical data. In order to make a diagnostic of w(z), the introduction of a null test of dark energy can be done using a diagnostic function of redshift, Om. In this work we present a nonparametric reconstruction of this diagnostic using the so-called Loess-Simex factory to test the concordance model with the advantage that this approach offers an alternative way to relax the use of priors and find a possible 'w' that reliably describe the data with no previous knowledge of a cosmological model. Our results demonstrate that the method applied to the dynamical Om diagnostic finds a preference for a dark energy model with equation of state w =-2/3, which correspond to a static domain wall network.
Evaluation of Nonparametric Probabilistic Forecasts of Wind Power
DEFF Research Database (Denmark)
Pinson, Pierre; Møller, Jan Kloppenborg; Nielsen, Henrik Aalborg, orlov 31.07.2008;
likely outcome for each look-ahead time, but also with uncertainty estimates given by probabilistic forecasts. In order to avoid assumptions on the shape of predictive distributions, these probabilistic predictions are produced from nonparametric methods, and then take the form of a single or a set...... of quantile forecasts. The required and desirable properties of such probabilistic forecasts are defined and a framework for their evaluation is proposed. This framework is applied for evaluating the quality of two statistical methods producing full predictive distributions from point predictions of wind......Predictions of wind power production for horizons up to 48-72 hour ahead comprise a highly valuable input to the methods for the daily management or trading of wind generation. Today, users of wind power predictions are not only provided with point predictions, which are estimates of the most...
Exact Probability Distribution versus Entropy
Directory of Open Access Journals (Sweden)
Kerstin Andersson
2014-10-01
Full Text Available The problem addressed concerns the determination of the average number of successive attempts of guessing a word of a certain length consisting of letters with given probabilities of occurrence. Both first- and second-order approximations to a natural language are considered. The guessing strategy used is guessing words in decreasing order of probability. When word and alphabet sizes are large, approximations are necessary in order to estimate the number of guesses. Several kinds of approximations are discussed demonstrating moderate requirements regarding both memory and central processing unit (CPU time. When considering realistic sizes of alphabets and words (100, the number of guesses can be estimated within minutes with reasonable accuracy (a few percent and may therefore constitute an alternative to, e.g., various entropy expressions. For many probability distributions, the density of the logarithm of probability products is close to a normal distribution. For those cases, it is possible to derive an analytical expression for the average number of guesses. The proportion of guesses needed on average compared to the total number decreases almost exponentially with the word length. The leading term in an asymptotic expansion can be used to estimate the number of guesses for large word lengths. Comparisons with analytical lower bounds and entropy expressions are also provided.
Can confidence indicators forecast the probability of expansion in Croatia?
Directory of Open Access Journals (Sweden)
Mirjana Čižmešija
2016-04-01
Full Text Available The aim of this paper is to investigate how reliable are confidence indicators in forecasting the probability of expansion. We consider three Croatian Business Survey indicators: the Industrial Confidence Indicator (ICI, the Construction Confidence Indicator (BCI and the Retail Trade Confidence Indicator (RTCI. The quarterly data, used in the research, covered the periods from 1999/Q1 to 2014/Q1. Empirical analysis consists of two parts. The non-parametric Bry-Boschan algorithm is used for distinguishing periods of expansion from the period of recession in the Croatian economy. Then, various nonlinear probit models were estimated. The models differ with respect to the regressors (confidence indicators and the time lags. The positive signs of estimated parameters suggest that the probability of expansion increases with an increase in Confidence Indicators. Based on the obtained results, the conclusion is that ICI is the most powerful predictor of the probability of expansion in Croatia.
Equity and efficiency in private and public education: a nonparametric comparison
L. Cherchye; K. de Witte; E. Ooghe; I. Nicaise
2007-01-01
We present a nonparametric approach for the equity and efficiency evaluation of (private and public) primary schools in Flanders. First, we use a nonparametric (Data Envelopment Analysis) model that is specially tailored to assess educational efficiency at the pupil level. The model accounts for the
Song, Dong; Wang, Zhuo; Marmarelis, Vasilis Z; Berger, Theodore W
2009-02-01
This paper presents a synergistic parametric and non-parametric modeling study of short-term plasticity (STP) in the Schaffer collateral to hippocampal CA1 pyramidal neuron (SC) synapse. Parametric models in the form of sets of differential and algebraic equations have been proposed on the basis of the current understanding of biological mechanisms active within the system. Non-parametric Poisson-Volterra models are obtained herein from broadband experimental input-output data. The non-parametric model is shown to provide better prediction of the experimental output than a parametric model with a single set of facilitation/depression (FD) process. The parametric model is then validated in terms of its input-output transformational properties using the non-parametric model since the latter constitutes a canonical and more complete representation of the synaptic nonlinear dynamics. Furthermore, discrepancies between the experimentally-derived non-parametric model and the equivalent non-parametric model of the parametric model suggest the presence of multiple FD processes in the SC synapses. Inclusion of an additional set of FD process in the parametric model makes it replicate better the characteristics of the experimentally-derived non-parametric model. This improved parametric model in turn provides the requisite biological interpretability that the non-parametric model lacks.
Out-of-Sample Extensions for Non-Parametric Kernel Methods.
Pan, Binbin; Chen, Wen-Sheng; Chen, Bo; Xu, Chen; Lai, Jianhuang
2017-02-01
Choosing suitable kernels plays an important role in the performance of kernel methods. Recently, a number of studies were devoted to developing nonparametric kernels. Without assuming any parametric form of the target kernel, nonparametric kernel learning offers a flexible scheme to utilize the information of the data, which may potentially characterize the data similarity better. The kernel methods using nonparametric kernels are referred to as nonparametric kernel methods. However, many nonparametric kernel methods are restricted to transductive learning, where the prediction function is defined only over the data points given beforehand. They have no straightforward extension for the out-of-sample data points, and thus cannot be applied to inductive learning. In this paper, we show how to make the nonparametric kernel methods applicable to inductive learning. The key problem of out-of-sample extension is how to extend the nonparametric kernel matrix to the corresponding kernel function. A regression approach in the hyper reproducing kernel Hilbert space is proposed to solve this problem. Empirical results indicate that the out-of-sample performance is comparable to the in-sample performance in most cases. Experiments on face recognition demonstrate the superiority of our nonparametric kernel method over the state-of-the-art parametric kernel methods.
Non-parametric tests of productive efficiency with errors-in-variables
Kuosmanen, T.K.; Post, T.; Scholtes, S.
2007-01-01
We develop a non-parametric test of productive efficiency that accounts for errors-in-variables, following the approach of Varian. [1985. Nonparametric analysis of optimizing behavior with measurement error. Journal of Econometrics 30(1/2), 445-458]. The test is based on the general Pareto-Koopmans
Equity and efficiency in private and public education: a nonparametric comparison
Cherchye, L.; de Witte, K.; Ooghe, E.; Nicaise, I.
2007-01-01
We present a nonparametric approach for the equity and efficiency evaluation of (private and public) primary schools in Flanders. First, we use a nonparametric (Data Envelopment Analysis) model that is specially tailored to assess educational efficiency at the pupil level. The model accounts for the
Comparison of non-parametric methods for ungrouping coarsely aggregated data
Directory of Open Access Journals (Sweden)
Silvia Rizzi
2016-05-01
Full Text Available Abstract Background Histograms are a common tool to estimate densities non-parametrically. They are extensively encountered in health sciences to summarize data in a compact format. Examples are age-specific distributions of death or onset of diseases grouped in 5-years age classes with an open-ended age group at the highest ages. When histogram intervals are too coarse, information is lost and comparison between histograms with different boundaries is arduous. In these cases it is useful to estimate detailed distributions from grouped data. Methods From an extensive literature search we identify five methods for ungrouping count data. We compare the performance of two spline interpolation methods, two kernel density estimators and a penalized composite link model first via a simulation study and then with empirical data obtained from the NORDCAN Database. All methods analyzed can be used to estimate differently shaped distributions; can handle unequal interval length; and allow stretches of 0 counts. Results The methods show similar performance when the grouping scheme is relatively narrow, i.e. 5-years age classes. With coarser age intervals, i.e. in the presence of open-ended age groups, the penalized composite link model performs the best. Conclusion We give an overview and test different methods to estimate detailed distributions from grouped count data. Health researchers can benefit from these versatile methods, which are ready for use in the statistical software R. We recommend using the penalized composite link model when data are grouped in wide age classes.
Probability distributions for multimeric systems.
Albert, Jaroslav; Rooman, Marianne
2016-01-01
We propose a fast and accurate method of obtaining the equilibrium mono-modal joint probability distributions for multimeric systems. The method necessitates only two assumptions: the copy number of all species of molecule may be treated as continuous; and, the probability density functions (pdf) are well-approximated by multivariate skew normal distributions (MSND). Starting from the master equation, we convert the problem into a set of equations for the statistical moments which are then expressed in terms of the parameters intrinsic to the MSND. Using an optimization package on Mathematica, we minimize a Euclidian distance function comprising of a sum of the squared difference between the left and the right hand sides of these equations. Comparison of results obtained via our method with those rendered by the Gillespie algorithm demonstrates our method to be highly accurate as well as efficient.
Semi-parametric regression: Efficiency gains from modeling the nonparametric part
Yu, Kyusang; Park, Byeong U; 10.3150/10-BEJ296
2011-01-01
It is widely admitted that structured nonparametric modeling that circumvents the curse of dimensionality is important in nonparametric estimation. In this paper we show that the same holds for semi-parametric estimation. We argue that estimation of the parametric component of a semi-parametric model can be improved essentially when more structure is put into the nonparametric part of the model. We illustrate this for the partially linear model, and investigate efficiency gains when the nonparametric part of the model has an additive structure. We present the semi-parametric Fisher information bound for estimating the parametric part of the partially linear additive model and provide semi-parametric efficient estimators for which we use a smooth backfitting technique to deal with the additive nonparametric part. We also present the finite sample performances of the proposed estimators and analyze Boston housing data as an illustration.
Billingsley, Patrick
2012-01-01
Praise for the Third Edition "It is, as far as I'm concerned, among the best books in math ever written....if you are a mathematician and want to have the top reference in probability, this is it." (Amazon.com, January 2006) A complete and comprehensive classic in probability and measure theory Probability and Measure, Anniversary Edition by Patrick Billingsley celebrates the achievements and advancements that have made this book a classic in its field for the past 35 years. Now re-issued in a new style and format, but with the reliable content that the third edition was revered for, this
Ramajo, Julián; Cordero, José Manuel; Márquez, Miguel Ángel
2017-10-01
This paper analyses region-level technical efficiency in nine European countries over the 1995-2007 period. We propose the application of a nonparametric conditional frontier approach to account for the presence of heterogeneous conditions in the form of geographical externalities. Such environmental factors are beyond the control of regional authorities, but may affect the production function. Therefore, they need to be considered in the frontier estimation. Specifically, a spatial autoregressive term is included as an external conditioning factor in a robust order- m model. Thus we can test the hypothesis of non-separability (the external factor impacts both the input-output space and the distribution of efficiencies), demonstrating the existence of significant global interregional spillovers into the production process. Our findings show that geographical externalities affect both the frontier level and the probability of being more or less efficient. Specifically, the results support the fact that the spatial lag variable has an inverted U-shaped non-linear impact on the performance of regions. This finding can be interpreted as a differential effect of interregional spillovers depending on the size of the neighboring economies: positive externalities for small values, possibly related to agglomeration economies, and negative externalities for high values, indicating the possibility of production congestion. Additionally, evidence of the existence of a strong geographic pattern of European regional efficiency is reported and the levels of technical efficiency are acknowledged to have converged during the period under analysis.
Decision making in coal mine planning using a non-parametric technique of indicator kriging
Energy Technology Data Exchange (ETDEWEB)
Mamurekli, D. [Hacettepe University, Ankara (Turkey). Mining Engineering Dept.
1997-03-01
In countries where low calorific value coal reserves are abundant and oil reserves are short or none, the requirement of energy production is mainly supported by coal-fired power stations. Consequently, planning to mine the low calorific value coal deposits gains much importance considering the technical and environmental restrictions. Such a mine in Kangal Town of Sivas City is the one that delivers run of mine coal directly to the power station built in the region. In case the calorific value and the ash content of the extracted coal are lower and higher than the required limits, 1300 kcal/kg and 21%, respectively, the power station may apply penalties to the coal producing company. Since the delivery is continuous and made by relying on in situ determination of pre-estimated values these assessments without defining any confidence levels are inevitably subject to inaccuracy. Thus, the company should be aware of uncertainties in making decisions and avoid conceivable risks. In this study, valuable information is provided in the form of conditional distribution to be used during planning process. It maps the indicator variogram corresponding to calorific value of 1300 kcal/kg and the ash content of 21% estimating the conditional probabilities that the true ash contents are less and calorific values are higher than the critical limits by the application of non-parametric technique, indicator kriging. In addition, it outlines the areas that are most uncertain for decision making. 4 refs., 8 figs., 3 tabs.
Nonparametric signal processing validation in T-wave alternans detection and estimation.
Goya-Esteban, R; Barquero-Pérez, O; Blanco-Velasco, M; Caamaño-Fernández, A J; García-Alberola, A; Rojo-Álvarez, J L
2014-04-01
Although a number of methods have been proposed for T-Wave Alternans (TWA) detection and estimation, their performance strongly depends on their signal processing stages and on their free parameters tuning. The dependence of the system quality with respect to the main signal processing stages in TWA algorithms has not yet been studied. This study seeks to optimize the final performance of the system by successive comparisons of pairs of TWA analysis systems, with one single processing difference between them. For this purpose, a set of decision statistics are proposed to evaluate the performance, and a nonparametric hypothesis test (from Bootstrap resampling) is used to make systematic decisions. Both the temporal method (TM) and the spectral method (SM) are analyzed in this study. The experiments were carried out in two datasets: first, in semisynthetic signals with artificial alternant waves and added noise; second, in two public Holter databases with different documented risk of sudden cardiac death. For semisynthetic signals (SNR = 15 dB), after the optimization procedure, a reduction of 34.0% (TM) and 5.2% (SM) of the power of TWA amplitude estimation errors was achieved, and the power of error probability was reduced by 74.7% (SM). For Holter databases, appropriate tuning of several processing blocks, led to a larger intergroup separation between the two populations for TWA amplitude estimation. Our proposal can be used as a systematic procedure for signal processing block optimization in TWA algorithmic implementations.