Estimation in autoregressive models with Markov regime
Ríos, Ricardo; Rodríguez, Luis
2005-01-01
In this paper we derive the consistency of the penalized likelihood method for the number state of the hidden Markov chain in autoregressive models with Markov regimen. Using a SAEM type algorithm to estimate the models parameters. We test the null hypothesis of hidden Markov Model against an autoregressive process with Markov regime.
A new approach to simulating stream isotope dynamics using Markov switching autoregressive models
Birkel, Christian; Paroli, Roberta; Spezia, Luigi; Dunn, Sarah M.; Tetzlaff, Doerthe; Soulsby, Chris
2012-09-01
In this study we applied Markov switching autoregressive models (MSARMs) as a proof-of-concept to analyze the temporal dynamics and statistical characteristics of the time series of two conservative water isotopes, deuterium (δ2H) and oxygen-18 (δ18O), in daily stream water samples over two years in a small catchment in eastern Scotland. MSARMs enabled us to explicitly account for the identified non-linear, non-Normal and non-stationary isotope dynamics of both time series. The hidden states of the Markov chain could also be associated with meteorological and hydrological drivers identifying the short (event) and longer-term (inter-event) transport mechanisms for both isotopes. Inference was based on the Bayesian approach performed through Markov Chain Monte Carlo algorithms, which also allowed us to deal with a high rate of missing values (17%). Although it is usually assumed that both isotopes are conservative and exhibit similar dynamics, δ18O showed somewhat different time series characteristics. Both isotopes were best modelled with two hidden states, but δ18O demanded autoregressions of the first order, whereas δ2H of the second. Moreover, both the dynamics of observations and the hidden states of the two isotopes were explained by two different sets of covariates. Consequently use of the two tracers for transit time modelling and hydrograph separation may result in different interpretations on the functioning of a catchment system.
Birkel, C.; Paroli, R.; Spezia, L.; Tetzlaff, D.; Soulsby, C.
2012-12-01
In this paper we present a novel model framework using the class of Markov Switching Autoregressive Models (MSARMs) to examine catchments as complex stochastic systems that exhibit non-stationary, non-linear and non-Normal rainfall-runoff and solute dynamics. Hereby, MSARMs are pairs of stochastic processes, one observed and one unobserved, or hidden. We model the unobserved process as a finite state Markov chain and assume that the observed process, given the hidden Markov chain, is conditionally autoregressive, which means that the current observation depends on its recent past (system memory). The model is fully embedded in a Bayesian analysis based on Markov Chain Monte Carlo (MCMC) algorithms for model selection and uncertainty assessment. Hereby, the autoregressive order and the dimension of the hidden Markov chain state-space are essentially self-selected. The hidden states of the Markov chain represent unobserved levels of variability in the observed process that may result from complex interactions of hydroclimatic variability on the one hand and catchment characteristics affecting water and solute storage on the other. To deal with non-stationarity, additional meteorological and hydrological time series along with a periodic component can be included in the MSARMs as covariates. This extension allows identification of potential underlying drivers of temporal rainfall-runoff and solute dynamics. We applied the MSAR model framework to streamflow and conservative tracer (deuterium and oxygen-18) time series from an intensively monitored 2.3 km2 experimental catchment in eastern Scotland. Statistical time series analysis, in the form of MSARMs, suggested that the streamflow and isotope tracer time series are not controlled by simple linear rules. MSARMs showed that the dependence of current observations on past inputs observed by transport models often in form of the long-tailing of travel time and residence time distributions can be efficiently explained by
Githure John I
2009-09-01
Full Text Available Abstract Background Autoregressive regression coefficients for Anopheles arabiensis aquatic habitat models are usually assessed using global error techniques and are reported as error covariance matrices. A global statistic, however, will summarize error estimates from multiple habitat locations. This makes it difficult to identify where there are clusters of An. arabiensis aquatic habitats of acceptable prediction. It is therefore useful to conduct some form of spatial error analysis to detect clusters of An. arabiensis aquatic habitats based on uncertainty residuals from individual sampled habitats. In this research, a method of error estimation for spatial simulation models was demonstrated using autocorrelation indices and eigenfunction spatial filters to distinguish among the effects of parameter uncertainty on a stochastic simulation of ecological sampled Anopheles aquatic habitat covariates. A test for diagnostic checking error residuals in an An. arabiensis aquatic habitat model may enable intervention efforts targeting productive habitats clusters, based on larval/pupal productivity, by using the asymptotic distribution of parameter estimates from a residual autocovariance matrix. The models considered in this research extends a normal regression analysis previously considered in the literature. Methods Field and remote-sampled data were collected during July 2006 to December 2007 in Karima rice-village complex in Mwea, Kenya. SAS 9.1.4® was used to explore univariate statistics, correlations, distributions, and to generate global autocorrelation statistics from the ecological sampled datasets. A local autocorrelation index was also generated using spatial covariance parameters (i.e., Moran's Indices in a SAS/GIS® database. The Moran's statistic was decomposed into orthogonal and uncorrelated synthetic map pattern components using a Poisson model with a gamma-distributed mean (i.e. negative binomial regression. The eigenfunction
A flexible prior distribution for Markov switching autoregressions with Student-t errors
Philippe J. DESCHAMPS
2012-01-01
This paper proposes an empirical Bayes approach for Markov switching autoregressions that can constrain some of the state-dependent parameters (regression coefficients and error variances) to be approximately equal across regimes. By flexibly reducing the dimension of the parameter space, this can help to ensure regime separation and to detect the Markov switching nature of the data. The permutation sampler with a hierarchical prior is used for choosing the prior moments, the identification c...
Michael Seifert
Full Text Available Changes in gene expression programs play a central role in cancer. Chromosomal aberrations such as deletions, duplications and translocations of DNA segments can lead to highly significant positive correlations of gene expression levels of neighboring genes. This should be utilized to improve the analysis of tumor expression profiles. Here, we develop a novel model class of autoregressive higher-order Hidden Markov Models (HMMs that carefully exploit local data-dependent chromosomal dependencies to improve the identification of differentially expressed genes in tumor. Autoregressive higher-order HMMs overcome generally existing limitations of standard first-order HMMs in the modeling of dependencies between genes in close chromosomal proximity by the simultaneous usage of higher-order state-transitions and autoregressive emissions as novel model features. We apply autoregressive higher-order HMMs to the analysis of breast cancer and glioma gene expression data and perform in-depth model evaluation studies. We find that autoregressive higher-order HMMs clearly improve the identification of overexpressed genes with underlying gene copy number duplications in breast cancer in comparison to mixture models, standard first- and higher-order HMMs, and other related methods. The performance benefit is attributed to the simultaneous usage of higher-order state-transitions in combination with autoregressive emissions. This benefit could not be reached by using each of these two features independently. We also find that autoregressive higher-order HMMs are better able to identify differentially expressed genes in tumors independent of the underlying gene copy number status in comparison to the majority of related methods. This is further supported by the identification of well-known and of previously unreported hotspots of differential expression in glioblastomas demonstrating the efficacy of autoregressive higher-order HMMs for the analysis of individual
Bias-correction in vector autoregressive models: A simulation study
Engsted, Tom; Pedersen, Thomas Quistgaard
We analyze and compare the properties of various methods for bias-correcting parameter estimates in vector autoregressions. First, we show that two analytical bias formulas from the existing literature are in fact identical. Next, based on a detailed simulation study, we show that this simple and...... pushing an otherwise stationary model into the non-stationary region of the parameter space during the process of correcting for bias....
Pinson, Pierre; Madsen, Henrik
2008-01-01
Better modelling and forecasting of very short-term power fluctuations at large offshore wind farms may significantly enhance control and management strategies of their power output. The paper introduces a new methodology for modelling and forecasting such very short-term fluctuations. The proposed...... methodology is based on a Markov-switching autoregressive model with time-varying coefficients. An advantage of the method is that one can easily derive full predictive densities. The quality of this methodology is demonstrated from the test case of 2 large offshore wind farms in Denmark. The exercise...... consists in 1-step ahead forecasting exercise on time-series of wind generation with a time resolution of 10 minute. The quality of the introduced forecasting methodology and its interest for better understanding power fluctuations are finally discussed....
DONG Ming
2008-01-01
As a new maintenance method, CBM (condition based maintenance) is becoming more and more important for the health management of complicated and costly equipment. A prerequisite to widespread deployment of CBM technology and prac-tice in industry is effective diagnostics and prognostics. Recently, a pattern recog-nition technique called HMM (hidden Markov model) was widely used in many fields. However, due to some unrealistic assumptions, diagnositic results from HMM were not so good, and it was difficult to use HMM directly for prognosis. By relaxing the unrealistic assumptions in HMM, this paper presents a novel approach to equip-ment health management based on auto-regressive hidden semi-Markov model (AR-HSMM). Compared with HMM, AR-HSMM has three advantages: 1)It allows explicitly modeling the time duration of the hidden states and therefore is capable of prognosis. 2) It can relax observations' independence assumption by accom-modating a link between consecutive observations. 3) It does not follow the unre-alistic Markov chain's memoryless assumption and therefore provides more pow-erful modeling and analysis capability for real problems. To facilitate the computation in the proposed AR-HSMM-based diagnostics and prognostics, new forwardbackward variables are defined and a modified forward-backward algorithm is developed. The evaluation of the proposed methodology was carried out through a real world application case study: health diagnosis and prognosis of hydraulic pumps in Caterpillar Inc. The testing results show that the proposed new approach based on AR-HSMM is effective and can provide useful support for the decision-making in equipment health management.
Pinson, Pierre; Madsen, Henrik
Wind power production data at temporal resolutions of a few minutes exhibits successive periods with fluctuations of various dynamic nature and magnitude, which cannot be explained (so far) by the evolution of some explanatory variable. Our proposal is to capture this regime-switching behaviour...... recursively optimized is based on penalized maximum-likelihood, with exponential forgetting of past observations. MSAR models are then employed for 1-step-ahead point forecasting of 10-minute resolution time-series of wind power at two large offshore wind farms. They are favourably compared against...... persistence and AutoRegressive (AR) models. It is finally shown that the main interest of MSAR models lies in their ability to generate interval/density forecasts of significantly higher skill....
Pinson, Pierre; Madsen, Henrik
2012-01-01
Wind power production data at temporal resolutions of a few minutes exhibit successive periods with fluctuations of various dynamic nature and magnitude, which cannot be explained (so far) by the evolution of some explanatory variable. Our proposal is to capture this regime-switching behaviour with...... recursively optimized is based on penalized maximum likelihood, with exponential forgetting of past observations. MSAR models are then employed for one-step-ahead point forecasting of 10 min resolution time series of wind power at two large offshore wind farms. They are favourably compared against persistence...... and autoregressive models. It is finally shown that the main interest of MSAR models lies in their ability to generate interval/density forecasts of significantly higher skill....
Revisiting Weak Simulation for Substochastic Markov Chains
Jansen, David N.; Song, Lei; Zhang, Lijun
2013-01-01
The spectrum of branching-time relations for probabilistic systems has been investigated thoroughly by Baier, Hermanns, Katoen and Wolf (2003, 2005), including weak simulation for systems involving substochastic distributions. Weak simulation was proven to be sound w.r.t. the liveness fragment...... of the logic PCTL\\x, and its completeness was conjectured. We revisit this result and show that soundness does not hold in general, but only for Markov chains without divergence. It is refuted for some systems with substochastic distributions. Moreover, we provide a counterexample to completeness....... In this paper, we present a novel definition that is sound for live PCTL\\x, and a variant that is both sound and complete. A long version of this article containing full proofs is available from [11]....
Markov chain analysis of single spin flip Ising simulations
The Markov processes defined by random and loop-based schemes for single spin flip attempts in Monte Carlo simulations of the 2D Ising model are investigated, by explicitly constructing their transition matrices. Their analysis reveals that loops over all lattice sites using a Metropolis-type single spin flip probability often do not define ergodic Markov chains, and have distorted dynamical properties even if they are ergodic. The transition matrices also enable a comparison of the dynamics of random versus loop spin selection and Glauber versus Metropolis probabilities
Vasios C.E.
2003-01-01
Full Text Available In the present work, a new method for the classification of Event Related Potentials (ERPs is proposed. The proposed method consists of two modules: the feature extraction module and the classification module. The feature extraction module comprises the implementation of the Multivariate Autoregressive model in conjunction with the Simulated Annealing technique, for the selection of optimum features from ERPs. The classification module is implemented with a single three-layer neural network, trained with the back-propagation algorithm and classifies the data into two classes: patients and control subjects. The method, in the form of a Decision Support System (DSS, has been thoroughly tested to a number of patient data (OCD, FES, depressives and drug users, resulting successful classification up to 100%.
Carlos Alejandro De Luna Ortega
2006-01-01
Full Text Available En este artículo se aborda el diseño de un reconocedor de voz, con el idioma español mexicano, del estado de Aguascalientes, de palabras aisladas, con dependencia del hablante y vocabulario pequeño, empleando Redes Neuronales Artificiales (ANN por sus siglas en inglés, Alineamiento Dinámico del Tiempo (DTW por sus siglas en inglés y Modelos Ocultos de Markov (HMM por sus siglas en inglés para la realización del algoritmo de reconocimiento.
Parallel algorithms for simulating continuous time Markov chains
Nicol, David M.; Heidelberger, Philip
1992-01-01
We have previously shown that the mathematical technique of uniformization can serve as the basis of synchronization for the parallel simulation of continuous-time Markov chains. This paper reviews the basic method and compares five different methods based on uniformization, evaluating their strengths and weaknesses as a function of problem characteristics. The methods vary in their use of optimism, logical aggregation, communication management, and adaptivity. Performance evaluation is conducted on the Intel Touchstone Delta multiprocessor, using up to 256 processors.
Cost Effective Community Based Dementia Screening: A Markov Model Simulation
Erin Saito
2014-01-01
Full Text Available Background. Given the dementia epidemic and the increasing cost of healthcare, there is a need to assess the economic benefit of community based dementia screening programs. Materials and Methods. Markov model simulations were generated using data obtained from a community based dementia screening program over a one-year period. The models simulated yearly costs of caring for patients based on clinical transitions beginning in pre dementia and extending for 10 years. Results. A total of 93 individuals (74 female, 19 male were screened for dementia and 12 meeting clinical criteria for either mild cognitive impairment (n=7 or dementia (n=5 were identified. Assuming early therapeutic intervention beginning during the year of dementia detection, Markov model simulations demonstrated 9.8% reduction in cost of dementia care over a ten-year simulation period, primarily through increased duration in mild stages and reduced time in more costly moderate and severe stages. Discussion. Community based dementia screening can reduce healthcare costs associated with caring for demented individuals through earlier detection and treatment, resulting in proportionately reduced time in more costly advanced stages.
Variance reduction techniques in the simulation of Markov processes
We study a functional r of the stationary distribution of a homogeneous Markov chain. It is often difficult or impossible to perform the analytical calculation of r and so it is reasonable to estimate r by a simulation process. A consistent estimator r(n) of r is obtained with respect to a chain with a countable state space. Suitably modifying the estimator r(n) of r one obtains a new consistent estimator which has a smaller variance than r(n). The same is obtained in the case of finite state space
Fokianos, Konstantinos; Rahbek, Anders Christian; Tjøstheim, Dag
This paper considers geometric ergodicity and likelihood based inference for linear and nonlinear Poisson autoregressions. In the linear case the conditional mean is linked linearly to its past values as well as the observed values of the Poisson process. This also applies to the conditional...... variance, implying an interpretation as an integer valued GARCH process. In a nonlinear conditional Poisson model, the conditional mean is a nonlinear function of its past values and a nonlinear function of past observations. As a particular example an exponential autoregressive Poisson model for time...
Fokianos, Konstantinos; Rahbæk, Anders; Tjøstheim, Dag
This paper considers geometric ergodicity and likelihood based inference for linear and nonlinear Poisson autoregressions. In the linear case the conditional mean is linked linearly to its past values as well as the observed values of the Poisson process. This also applies to the conditional...... variance, making an interpretation as an integer valued GARCH process possible. In a nonlinear conditional Poisson model, the conditional mean is a nonlinear function of its past values and a nonlinear function of past observations. As a particular example an exponential autoregressive Poisson model for...
刘震; 王厚军; 龙兵; 张治国
2009-01-01
针对电子系统状态趋势预测问题,提出了一种加权隐马尔可夫模型的自回归趋势预测方法.该方法以自回归模型作为隐马尔可夫的状态输出,利用加权预测思想对马尔可夫链中的隐状态进行混合高斯模型的加权序列预测,并利用最大概率隐状态下的自回归系数计算模型输出.通过对实际的复杂混沌序列和电子系统BIT状态数据进行趋势预测,并针对不同模型参数下的预测结果进行实验分析,结果表明该方法对系统状态变化的趋势具有较好的预测性能.%A novel trend prediction approach based on weighed hidden Markov model (HMM) and autoregressive model (AR) is presented in order to solve this problem of bend prediction for complex electronic system. This approach regards the autoregressive model as the output of HMM, uses weighted prediction method and mixed Gaussianin model to predict the hidden state of Markov chain,and calculates the output of model by using the regression coefficient of the maximum probability hidden state. This approach is applied to the trend prediction of complex chaotic time series and typical electronic equipment's BIT data, and the effects of various model parameters on trend prediction precision are discussed.The experiments based on condition trend prediction for electronic equipments demonstrate the effectiveness of the method.
Simulation of daily rainfall through markov chain modeling
Being an agricultural country, the inhabitants of dry land in cultivated areas mainly rely on the daily rainfall for watering their fields. A stochastic model based on first order Markov Chain was developed to simulate daily rainfall data for Multan, D. I. Khan, Nawabshah, Chilas and Barkhan for the period 1981-2010. Transitional probability matrices of first order Markov Chain was utilized to generate the daily rainfall occurrence while gamma distribution was used to generate the daily rainfall amount. In order to achieve the parametric values of mentioned cities, method of moments is used to estimate the shape and scale parameters which lead to synthetic sequence generation as per gamma distribution. In this study, unconditional and conditional probabilities of wet and dry days in sum with means and standard deviations are considered as the essential parameters for the simulated stochastic generation of daily rainfalls. It has been found that the computerized synthetic rainfall series concurred pretty well with the actual observed rainfall series. (author)
Noncausal Bayesian Vector Autoregression
Lanne, Markku; Luoto, Jani
We propose a Bayesian inferential procedure for the noncausal vector autoregressive (VAR) model that is capable of capturing nonlinearities and incorporating effects of missing variables. In particular, we devise a fast and reliable posterior simulator that yields the predictive distribution as a...
Simulation-based algorithms for Markov decision processes
Chang, Hyeong Soo; Fu, Michael C; Marcus, Steven I
2013-01-01
Markov decision process (MDP) models are widely used for modeling sequential decision-making problems that arise in engineering, economics, computer science, and the social sciences. Many real-world problems modeled by MDPs have huge state and/or action spaces, giving an opening to the curse of dimensionality and so making practical solution of the resulting models intractable. In other cases, the system of interest is too complex to allow explicit specification of some of the MDP model parameters, but simulation samples are readily available (e.g., for random transitions and costs). For these settings, various sampling and population-based algorithms have been developed to overcome the difficulties of computing an optimal solution in terms of a policy and/or value function. Specific approaches include adaptive sampling, evolutionary policy iteration, evolutionary random policy search, and model reference adaptive search. This substantially enlarged new edition reflects the latest developments in novel ...
English, Thomas
2005-01-01
A standard tool of reliability analysis used at NASA-JSC is the event tree. An event tree is simply a probability tree, with the probabilities determining the next step through the tree specified at each node. The nodal probabilities are determined by a reliability study of the physical system at work for a particular node. The reliability study performed at a node is typically referred to as a fault tree analysis, with the potential of a fault tree existing.for each node on the event tree. When examining an event tree it is obvious why the event tree/fault tree approach has been adopted. Typical event trees are quite complex in nature, and the event tree/fault tree approach provides a systematic and organized approach to reliability analysis. The purpose of this study was two fold. Firstly, we wanted to explore the possibility that a semi-Markov process can create dependencies between sojourn times (the times it takes to transition from one state to the next) that can decrease the uncertainty when estimating time to failures. Using a generalized semi-Markov model, we studied a four element reliability model and were able to demonstrate such sojourn time dependencies. Secondly, we wanted to study the use of semi-Markov processes to introduce a time variable into the event tree diagrams that are commonly developed in PRA (Probabilistic Risk Assessment) analyses. Event tree end states which change with time are more representative of failure scenarios than are the usual static probability-derived end states.
Srinath, Sriakr; Rudy, Alexander R; Ammons, S Mark
2015-01-01
We present a sample-based, autoregressive (AR) method for the generation and time evolution of atmospheric phase screens that is computationally efficient and uses a single parameter per Fourier mode to vary the power contained in the frozen flow and stochastic components. We address limitations of Fourier-based methods such as screen periodicity and low spatial frequency power content. Comparisons of adaptive optics (AO) simulator performance when fed AR phase screens and translating phase screens reveal significantly elevated residual closed-loop temporal power for small increases in added stochastic content at each time step, thus displaying the importance of properly modeling atmospheric "boiling". We present preliminary evidence that our model fits to AO telemetry are better reflections of real conditions than the pure frozen flow assumption.
Using Markov models to simulate electron spin resonance spectra from molecular dynamics trajectories
Sezer, Deniz; Freed, Jack H.; Roux, Benoît
2008-01-01
Simulating electron spin resonance (ESR) spectra directly from molecular dynamics simulations of a spin labeled protein necessitates a large number (hundreds or thousands) of relatively long (hundreds of ns) trajectories. To meet this challenge, we explore the possibility of constructing accurate stochastic models of the spin label dynamics from atomistic trajectories. A systematic, two-step procedure, based on the probabilistic framework of hidden Markov models, is developed to build a discr...
Simulation of ion movement in soil using a continuous-time Markov process
Simulation of solute transport using a continuous-time Markov process is a new approach for modeling chemical movement in soils. The authors describe the model and apply it to the results of tracer experiments on the transport of iodine, bromine, strontium and lithium in Bandalier tuff. The model successfully describes most of the data but was not able to simulate strontium displacement in the current study. The reasons for this are not clear
A fast exact simulation method for a class of Markov jump processes
A new method of the stochastic simulation algorithm (SSA), named the Hashing-Leaping method (HLM), for exact simulations of a class of Markov jump processes, is presented in this paper. The HLM has a conditional constant computational cost per event, which is independent of the number of exponential clocks in the Markov process. The main idea of the HLM is to repeatedly implement a hash-table-like bucket sort algorithm for all times of occurrence covered by a time step with length τ. This paper serves as an introduction to this new SSA method. We introduce the method, demonstrate its implementation, analyze its properties, and compare its performance with three other commonly used SSA methods in four examples. Our performance tests and CPU operation statistics show certain advantages of the HLM for large scale problems
RESTART Simulation of Non-Markov Consecutive-K-Out-of-N: F Repairable Systems
Villén Altamirano, José
2010-01-01
The reliability of consecutive-k-out-of-n: F repairable systems and (k−1)-step Markov dependence is studied. The model analyzed in this paper is more general than those of previous studies given that repair time and component lifetimes are random variables that follow a general distribution. The system has one repair service which adopts a priority repair rule based on system failure risk. Since crude simulation has proved to be inefficient for highly dependable systems, the RESTART method wa...
Bayesian Variable Selection in Spatial Autoregressive Models
Jesus Crespo Cuaresma; Philipp Piribauer
2015-01-01
This paper compares the performance of Bayesian variable selection approaches for spatial autoregressive models. We present two alternative approaches which can be implemented using Gibbs sampling methods in a straightforward way and allow us to deal with the problem of model uncertainty in spatial autoregressive models in a flexible and computationally efficient way. In a simulation study we show that the variable selection approaches tend to outperform existing Bayesian model averaging tech...
Rudzinski, Joseph F; Bereau, Tristan
2016-01-01
Molecular simulations can provide microscopic insight into the physical and chemical driving forces of complex molecular processes. Despite continued advancement of simulation methodology, model errors may lead to inconsistencies between simulated and reference (e.g., from experiments or higher-level simulations) observables. To bound the microscopic information generated by computer simulations within reference measurements, we propose a method that reweights the microscopic transitions of the system to improve consistency with a set of coarse kinetic observables. The method employs the well-developed Markov state modeling framework to efficiently link microscopic dynamics with long-time scale constraints, thereby consistently addressing a wide range of time scales. To emphasize the robustness of the method, we consider two distinct coarse-grained models with significant kinetic inconsistencies. When applied to the simulated conformational dynamics of small peptides, the reweighting procedure systematically ...
Stochastic Differential Equations and Markov Processes in the Modeling of Electrical Circuits
R. Rezaeyan
2010-06-01
Full Text Available Stochastic differential equations(SDEs, arise from physical systems that possess inherent noise and certainty. We derive a SDE for electrical circuits. In this paper, we will explore the close relationship between the SDE and autoregressive(AR model. We will solve SDE related to RC circuit with using of AR(1 model (Markov process and however with Euler-Maruyama(EM method. Then, we will compare this solutions. Numerical simulations in MATLAB are obtained.
刘芳; 毛志忠
2011-01-01
针对过程工业中强噪声环境下实时采集的控制过程海量数据难以在线精确检测的问题,提出了基于阶数自学习自回归隐马尔可夫模型(ARHMM)的工业控制过程异常数据在线检测方法.该算法采用自同归(AR)模型对时间序列进行拟合,利用隐马尔科夫模型(HMM)作为数据检测的工具,避免了传统检测方法中需要预先设定检测阈值的问题,并将传统的BDT(Brockwell-Dahlhaus-Trindade)算法改进成为对于时间和阶数均实施迭代的双重迭代结构,以实现ARHMM参数在线更新.为了减小异常数据对ARHMM参数更新的影响,本文采用先检测后更新的方式,根据检测结果采取不同的更新方法,提高了该算法的鲁棒性.模型数据仿真与应用试验结果证明,该算法具有较高的检测精度和抗干扰能力,同时具备在线检测的能力.通过与传统基于AR模型的异常数据检测方法比较,证明了该方法更适合作为过程工业控制过程数据的异常检测工具.%For the accurate online detection and collection of massive real-time data of a control process in strong noise environment, we propose an autoregressive hidden Markov model (AJRHMM) algorithm with order self-learning. This algorithm employs an AR model to fit the time series and makes use of the hidden Markov model as the basic detection tool for avoiding the deficiency in presetting the threshold in traditional detection methods. In order to update the parameters of ARHMM online, we adopt the improved traditional BDT(Brockwell-Dahlhaus-Trindade) algorithm with double iterative structures, in which the iterative calculations are performed respectively for both time and order. To reduce the influence of outlier on parameter updating in ARHMM, we adopt the strategy of detection-before-update, and select the method for updating based on the detection results. This strategy improves the robustness of the algorithm. Simulation with emulation data and
Zhao Zhi-Jin; Zheng Shi-Lian; Xu Chun-Yun; Kong Xian-Zheng
2007-01-01
Hidden Markov models (HMMs) have been used to model burst error sources of wireless channels. This paper proposes a hybrid method of using genetic algorithm (GA) and simulated annealing (SA) to train HMM for discrete channel modelling. The proposed method is compared with pure GA, and experimental results show that the HMMs trained by the hybrid method can better describe the error sequences due to SA's ability of facilitating hill-climbing at the later stage of the search. The burst error statistics of the HMMs trained by the proposed method and the corresponding error sequences are also presented to validate the proposed method.
Reliability assessments based on probabilistic fracture mechanics can give insight into the effects of changes in design parameters, operational conditions and maintenance schemes. Although they are often not capable of providing absolute reliability values, these methods at least allow the ranking of different solutions among alternatives. Due to the variety of possible solutions for design, operation and maintenance problems numerous probabilistic reliability assessments have to be carried out. This is a laborous task especially for crack containing welds of nuclear pipes subjected to fatigue. The objective of this paper is to compare the Monte Carlo simulation method and a newly developed approximative approach using the Markov process ansatz for this task
Vrugt, Jasper A [Los Alamos National Laboratory; Hyman, James M [Los Alamos National Laboratory; Robinson, Bruce A [Los Alamos National Laboratory; Higdon, Dave [Los Alamos National Laboratory; Ter Braak, Cajo J F [NETHERLANDS; Diks, Cees G H [UNIV OF AMSTERDAM
2008-01-01
Markov chain Monte Carlo (MCMC) methods have found widespread use in many fields of study to estimate the average properties of complex systems, and for posterior inference in a Bayesian framework. Existing theory and experiments prove convergence of well constructed MCMC schemes to the appropriate limiting distribution under a variety of different conditions. In practice, however this convergence is often observed to be disturbingly slow. This is frequently caused by an inappropriate selection of the proposal distribution used to generate trial moves in the Markov Chain. Here we show that significant improvements to the efficiency of MCMC simulation can be made by using a self-adaptive Differential Evolution learning strategy within a population-based evolutionary framework. This scheme, entitled DiffeRential Evolution Adaptive Metropolis or DREAM, runs multiple different chains simultaneously for global exploration, and automatically tunes the scale and orientation of the proposal distribution in randomized subspaces during the search. Ergodicity of the algorithm is proved, and various examples involving nonlinearity, high-dimensionality, and multimodality show that DREAM is generally superior to other adaptive MCMC sampling approaches. The DREAM scheme significantly enhances the applicability of MCMC simulation to complex, multi-modal search problems.
Rudzinski, Joseph F.; Kremer, Kurt; Bereau, Tristan
2016-02-01
Molecular simulations can provide microscopic insight into the physical and chemical driving forces of complex molecular processes. Despite continued advancement of simulation methodology, model errors may lead to inconsistencies between simulated and reference (e.g., from experiments or higher-level simulations) observables. To bound the microscopic information generated by computer simulations within reference measurements, we propose a method that reweights the microscopic transitions of the system to improve consistency with a set of coarse kinetic observables. The method employs the well-developed Markov state modeling framework to efficiently link microscopic dynamics with long-time scale constraints, thereby consistently addressing a wide range of time scales. To emphasize the robustness of the method, we consider two distinct coarse-grained models with significant kinetic inconsistencies. When applied to the simulated conformational dynamics of small peptides, the reweighting procedure systematically improves the time scale separation of the slowest processes. Additionally, constraining the forward and backward rates between metastable states leads to slight improvement of their relative stabilities and, thus, refined equilibrium properties of the resulting model. Finally, we find that difficulties in simultaneously describing both the simulated data and the provided constraints can help identify specific limitations of the underlying simulation approach.
A hidden Markov model combined with climate indices for multidecadal streamflow simulation
Bracken, C.; Rajagopalan, B.; Zagona, E.
2014-10-01
Hydroclimate time series often exhibit very low year-to-year autocorrelation while showing prolonged wet and dry epochs reminiscent of regime-shifting behavior. Traditional stochastic time series models cannot capture the regime-shifting features thereby misrepresenting the risk of prolonged wet and dry periods, consequently impacting management and planning efforts. Upper Colorado River Basin (UCRB) annual flow series highlights this clearly. To address this, a simulation framework is developed using a hidden Markov (HM) model in combination with large-scale climate indices that drive multidecadal variability. We demonstrate this on the UCRB flows and show that the simulations are able to capture the regime features by reproducing the multidecadal spectral features present in the data where a basic HM model without climate information cannot.
Simulating Replica Exchange: Markov State Models, Proposal Schemes, and the Infinite Swapping Limit.
Zhang, Bin W; Dai, Wei; Gallicchio, Emilio; He, Peng; Xia, Junchao; Tan, Zhiqiang; Levy, Ronald M
2016-08-25
Replica exchange molecular dynamics is a multicanonical simulation technique commonly used to enhance the sampling of solvated biomolecules on rugged free energy landscapes. While replica exchange is relatively easy to implement, there are many unanswered questions about how to use this technique most efficiently, especially because it is frequently the case in practice that replica exchange simulations are not fully converged. A replica exchange cycle consists of a series of molecular dynamics steps of a set of replicas moving under different Hamiltonians or at different thermodynamic states followed by one or more replica exchange attempts to swap replicas among the different states. How the replica exchange cycle is constructed affects how rapidly the system equilibrates. We have constructed a Markov state model of replica exchange (MSMRE) using long molecular dynamics simulations of a host-guest binding system as an example, in order to study how different implementations of the replica exchange cycle can affect the sampling efficiency. We analyze how the number of replica exchange attempts per cycle, the number of MD steps per cycle, and the interaction between the two parameters affects the largest implied time scale of the MSMRE simulation. The infinite swapping limit is an important concept in replica exchange. We show how to estimate the infinite swapping limit from the diagonal elements of the exchange transition matrix constructed from MSMRE "simulations of simulations" as well as from relatively short runs of the actual replica exchange simulations. PMID:27079355
Adu, Nurlia; Indriati Retno, P.; Suharsono
2016-02-01
Monitoring of micro seismic activity in the geothermal field is useful to know the fracture controllers in the geothermal reservoir area. However, in determining the point of micro earthquake, hypocenters still contain inherent uncertainties due to several factors such as mismatches velocity model used by the actual subsurface conditions. For that reason, hypocenter relocation by Markov Chain method is used, to simulate the hypocenter point spatially based opportunities transition containing the principle of conditional probability. The purpose of this relocation is to improve the models of the hypocenter so that the interpretation of the subsurface structure is better. From the result of the relocation of using Markov Chain identified fault structures trending below the surface of the northeast-southwest (NE-SW) with approximately N38°E. This structure is suspected as the continuity of the structure in the surface. The depth of the hypocenter is located 758 m above mean sea level more than 800 m below mean sea level.
Generalizing smooth transition autoregressions
Chini, Emilio Zanetti
We introduce a variant of the smooth transition autoregression - the GSTAR model - capable to parametrize the asymmetry in the tails of the transition equation by using a particular generalization of the logistic function. A General-to-Specific modelling strategy is discussed in detail, with part......We introduce a variant of the smooth transition autoregression - the GSTAR model - capable to parametrize the asymmetry in the tails of the transition equation by using a particular generalization of the logistic function. A General-to-Specific modelling strategy is discussed in detail...... forecasting experiment to evaluate its point and density forecasting performances. In all the cases, the dynamic asymmetry in the cycle is efficiently captured by the new model. The GSTAR beats AR and STAR competitors in point forecasting, while this superiority becomes less evident in density forecasting...
DIM SUM: demography and individual migration simulated using a Markov chain.
Brown, Jeremy M; Savidge, Kevin; McTavish, Emily Jane B
2011-03-01
An increasing number of studies seek to infer demographic history, often jointly with genetic relationships. Despite numerous analytical methods for such data, few simulations have investigated the methods' power and robustness, especially when underlying assumptions have been violated. DIM SUM (Demography and Individual Migration Simulated Using a Markov chain) is a stand-alone Java program for the simulation of population demography and individual migration while recording ancestor-descendant relationships. It does not employ coalescent assumptions or discrete population boundaries. It is extremely flexible, allowing the user to specify border positions, reactions of organisms to borders, local and global carrying capacities, individual dispersal kernels, rates of reproduction and strategies for sampling individuals. Spatial variables may be specified using image files (e.g., as exported from gis software) and may vary through time. In combination with software for genetic marker simulation, DIM SUM will be useful for testing phylogeographic (e.g., nested clade phylogeographic analysis, coalescent-based tests and continuous-landscape frameworks) and landscape-genetic methods, specifically regarding violations of coalescent assumptions. It can also be used to explore the qualitative features of proposed demographic scenarios (e.g. regarding biological invasions) and as a pedagogical tool. DIM SUM (with user's manual) can be downloaded from http://code.google.com/p/bio-dimsum. PMID:21429144
Autoregressive conditional beta
Yunmi Kim
2012-01-01
The capital asset pricing model provides various predictions about equilibrium expected returns on risky assets. One key prediction is that the risk premium on a risky asset is proportional to the nondiversifiable market risk measured by the asset's beta coefficient. This paper proposes a new method for estimating and drawing inferences from a time-varying capital asset pricing model. The proposed method, which can be considered a vector autoregressive model for multiple beta coefficients, is...
RESTART simulation of non-Markov consecutive-k-out-of-n: F repairable systems
Villen-Altamirano, Jose, E-mail: jvillen@eui.upm.e [Departamento de Matematica Aplicada (E.U. Informatica), Universidad Politecnica de Madrid, Calle Arboleda s/n, 28031 Madrid (Spain)
2010-03-15
The reliability of consecutive-k-out-of-n: F repairable systems and (k-1)-step Markov dependence is studied. The model analyzed in this paper is more general than those of previous studies given that repair time and component lifetimes are random variables that follow a general distribution. The system has one repair service which adopts a priority repair rule based on system failure risk. Since crude simulation has proved to be inefficient for highly dependable systems, the RESTART method was used for the estimation of steady-state unavailability, MTBF and unreliability. Probabilities up to the order of 10{sup -16} have been accurately estimated with little computational effort. In this method, a number of simulation retrials are performed when the process enters regions of the state space where the chance of occurrence of a rare event (e.g., a system failure) is higher. The main difficulty for the application of this method is to find a suitable function, called the importance function, to define the regions. Given the simplicity involved in changing some model assumptions with RESTART, the importance function used in this paper could be useful for dependability estimation of many systems.
RESTART simulation of non-Markov consecutive-k-out-of-n: F repairable systems
The reliability of consecutive-k-out-of-n: F repairable systems and (k-1)-step Markov dependence is studied. The model analyzed in this paper is more general than those of previous studies given that repair time and component lifetimes are random variables that follow a general distribution. The system has one repair service which adopts a priority repair rule based on system failure risk. Since crude simulation has proved to be inefficient for highly dependable systems, the RESTART method was used for the estimation of steady-state unavailability, MTBF and unreliability. Probabilities up to the order of 10-16 have been accurately estimated with little computational effort. In this method, a number of simulation retrials are performed when the process enters regions of the state space where the chance of occurrence of a rare event (e.g., a system failure) is higher. The main difficulty for the application of this method is to find a suitable function, called the importance function, to define the regions. Given the simplicity involved in changing some model assumptions with RESTART, the importance function used in this paper could be useful for dependability estimation of many systems.
Witowski, Vitali; Foraita, Ronja; Pitsiladis, Yannis; Pigeot, Iris; Wirsik, Norman
2014-01-01
Introduction The use of accelerometers to objectively measure physical activity (PA) has become the most preferred method of choice in recent years. Traditionally, cutpoints are used to assign impulse counts recorded by the devices to sedentary and activity ranges. Here, hidden Markov models (HMM) are used to improve the cutpoint method to achieve a more accurate identification of the sequence of modes of PA. Methods 1,000 days of labeled accelerometer data have been simulated. For the simulated data the actual sedentary behavior and activity range of each count is known. The cutpoint method is compared with HMMs based on the Poisson distribution (HMM[Pois]), the generalized Poisson distribution (HMM[GenPois]) and the Gaussian distribution (HMM[Gauss]) with regard to misclassification rate (MCR), bout detection, detection of the number of activities performed during the day and runtime. Results The cutpoint method had a misclassification rate (MCR) of 11% followed by HMM[Pois] with 8%, HMM[GenPois] with 3% and HMM[Gauss] having the best MCR with less than 2%. HMM[Gauss] detected the correct number of bouts in 12.8% of the days, HMM[GenPois] in 16.1%, HMM[Pois] and the cutpoint method in none. HMM[GenPois] identified the correct number of activities in 61.3% of the days, whereas HMM[Gauss] only in 26.8%. HMM[Pois] did not identify the correct number at all and seemed to overestimate the number of activities. Runtime varied between 0.01 seconds (cutpoint), 2.0 minutes (HMM[Gauss]) and 14.2 minutes (HMM[GenPois]). Conclusions Using simulated data, HMM-based methods were superior in activity classification when compared to the traditional cutpoint method and seem to be appropriate to model accelerometer data. Of the HMM-based methods, HMM[Gauss] seemed to be the most appropriate choice to assess real-life accelerometer data. PMID:25464514
Zeng, Xiaojun; Zhang, Liyun; Xiao, Xiuchan; Jiang, Yuanyuan; Guo, Yanzhi; Yu, Xinyan; Pu, Xuemei; Li, Menglong
2016-04-01
Thrombin-binding aptamer (TBA) with the sequence 5‧GGTTGGTGTGGTTGG3‧ could fold into G-quadruplex, which correlates with functionally important genomic regionsis. However, unfolding mechanism involved in the structural stability of G-quadruplex has not been satisfactorily elucidated on experiments so far. Herein, we studied the unfolding pathway of TBA by a combination of molecular dynamics simulation (MD) and Markov State Model (MSM). Our results revealed that the unfolding of TBA is not a simple two-state process but proceeds along multiple pathways with multistate intermediates. One high flux confirms some observations from NMR experiment. Another high flux exhibits a different and simpler unfolding pathway with less intermediates. Two important intermediate states were identified. One is similar to the G-triplex reported in the folding of G-quadruplex, but lack of H-bonding between guanines in the upper plane. More importantly, another intermediate state acting as a connector to link the folding region and the unfolding one, was the first time identified, which exhibits higher population and stability than the G-triplex-like intermediate. These results will provide valuable information for extending our understanding the folding landscape of G-quadruplex formation.
Dynamic temperature selection for parallel-tempering in Markov chain Monte Carlo simulations
Vousden, Will; Farr, Will M.; Mandel, Ilya
2015-01-01
Modern problems in astronomical Bayesian inference require efficient methods for sampling from complex, high-dimensional, often multi-modal probability distributions. Most popular methods, such as Markov chain Monte Carlo sampling, perform poorly on strongly multi-modal probability distributions, rarely jumping between modes or settling on just one mode without finding others. Parallel tempering addresses this problem by sampling simultaneously with separate Markov chains from tempered versio...
Vitali Witowski
Full Text Available INTRODUCTION: The use of accelerometers to objectively measure physical activity (PA has become the most preferred method of choice in recent years. Traditionally, cutpoints are used to assign impulse counts recorded by the devices to sedentary and activity ranges. Here, hidden Markov models (HMM are used to improve the cutpoint method to achieve a more accurate identification of the sequence of modes of PA. METHODS: 1,000 days of labeled accelerometer data have been simulated. For the simulated data the actual sedentary behavior and activity range of each count is known. The cutpoint method is compared with HMMs based on the Poisson distribution (HMM[Pois], the generalized Poisson distribution (HMM[GenPois] and the Gaussian distribution (HMM[Gauss] with regard to misclassification rate (MCR, bout detection, detection of the number of activities performed during the day and runtime. RESULTS: The cutpoint method had a misclassification rate (MCR of 11% followed by HMM[Pois] with 8%, HMM[GenPois] with 3% and HMM[Gauss] having the best MCR with less than 2%. HMM[Gauss] detected the correct number of bouts in 12.8% of the days, HMM[GenPois] in 16.1%, HMM[Pois] and the cutpoint method in none. HMM[GenPois] identified the correct number of activities in 61.3% of the days, whereas HMM[Gauss] only in 26.8%. HMM[Pois] did not identify the correct number at all and seemed to overestimate the number of activities. Runtime varied between 0.01 seconds (cutpoint, 2.0 minutes (HMM[Gauss] and 14.2 minutes (HMM[GenPois]. CONCLUSIONS: Using simulated data, HMM-based methods were superior in activity classification when compared to the traditional cutpoint method and seem to be appropriate to model accelerometer data. Of the HMM-based methods, HMM[Gauss] seemed to be the most appropriate choice to assess real-life accelerometer data.
Daniels, Noah M.; Hosur, Raghavendra; Berger, Bonnie; Lenore J Cowen
2012-01-01
Motivation: One of the most successful methods to date for recognizing protein sequences that are evolutionarily related has been profile hidden Markov models (HMMs). However, these models do not capture pairwise statistical preferences of residues that are hydrogen bonded in beta sheets. These dependencies have been partially captured in the HMM setting by simulated evolution in the training phase and can be fully captured by Markov random fields (MRFs). However, the MRFs can be computationa...
Jokar Arsanjani, J.; Helbich, M.; Kainz, W.; Boloorani, A.
2013-01-01
This research analyses the suburban expansion in the metropolitan area of Tehran, Iran. A hybrid model consisting of logistic regression model, Markov chain (MC), and cellular automata (CA) was designed to improve the performance of the standard logistic regression model. Environmental and socio-eco
Hobolth, Asger; Stone, Eric
2009-01-01
Analyses of serially-sampled data often begin with the assumption that the observations represent discrete samples from a latent continuous-time stochastic process. The continuous-time Markov chain (CTMC) is one such generative model whose popularity extends to a variety of disciplines ranging from...... computational finance to human genetics and genomics. A common theme among these diverse applications is the need to simulate sample paths of a CTMC conditional on realized data that is discretely observed. Here we present a general solution to this sampling problem when the CTMC is defined on a discrete and...
Dynamic temperature selection for parallel-tempering in Markov chain Monte Carlo simulations
Vousden, Will; Mandel, Ilya
2015-01-01
Modern problems in astronomical Bayesian inference require efficient methods for sampling from complex, high-dimensional, often multi-modal probability distributions. Most popular methods, such as Markov chain Monte Carlo sampling, perform poorly on strongly multi-modal probability distributions, rarely jumping between modes or settling on just one mode without finding others. Parallel tempering addresses this problem by sampling simultaneously with separate Markov chains from tempered versions of the target distribution with reduced contrast levels. Gaps between modes can be traversed at higher temperatures, while individual modes can be efficiently explored at lower temperatures. In this paper, we investigate how one might choose the ladder of temperatures to achieve lower autocorrelation time for the sampler (and therefore more efficient sampling). In particular, we present a simple, easily-implemented algorithm for dynamically adapting the temperature configuration of a sampler while sampling in order to ...
Approximate regenerative-block bootstrap for Markov chains: some simulation studies
Bertail, Patrice; Clémençon, Stéphan
2007-01-01
Abstract : In Bertail & Clémençon (2005a) a novel methodology for bootstrappinggeneral Harris Markov chains has been proposed, which crucially exploits their renewalproperties (when eventually extended via the Nummelin splitting technique) and has theoreticalproperties that surpass other existing methods within the Markovian framework(bmoving block bootstrap, sieve bootstrap etc...). This paper is devoted to discuss practicalissues related to the implementation of this specific resampling met...
Bias-correction in vector autoregressive models
Engsted, Tom; Pedersen, Thomas Quistgaard
2014-01-01
We analyze the properties of various methods for bias-correcting parameter estimates in both stationary and non-stationary vector autoregressive models. First, we show that two analytical bias formulas from the existing literature are in fact identical. Next, based on a detailed simulation study...... improvement over ordinary least squares. We pay special attention to the risk of pushing an otherwise stationary model into the non-stationary region of the parameter space when correcting for bias. Finally, we consider a recently proposed reduced-bias weighted least squares estimator, and we find that it...
Blind identification of threshold auto-regressive model for machine fault diagnosis
LI Zhinong; HE Yongyong; CHU Fulei; WU Zhaotong
2007-01-01
A blind identification method was developed for the threshold auto-regressive (TAR) model. The method had good identification accuracy and rapid convergence, especially for higher order systems. The proposed method was then combined with the hidden Markov model (HMM) to determine the auto-regressive (AR) coefficients for each interval used for feature extraction, with the HMM as a classifier. The fault diagnoses during the speed-up and speed- down processes for rotating machinery have been success- fully completed. The result of the experiment shows that the proposed method is practical and effective.
Markov-switching model for nonstationary runoff conditioned on El Nino information
Gelati, Emiliano; Madsen, H.; Rosbjerg, Dan
2010-01-01
We define a Markov-modulated autoregressive model with exogenous input (MARX) to generate runoff scenarios using climatic information. Runoff parameterization is assumed to be conditioned on a hidden climate state following a Markov chain, where state transition probabilities are functions...
Avdhesh Kr. Sharma
2012-10-01
Full Text Available In recent years, the availability of power plants has become increasingly important issue in most developed and developing countries. This paper aims to propose a methodology based on Markov approach to evaluate the availability simulation model for power generation system (Turbine in a thermal power plant under realistic working environment. The effects of occurrence of failure/course of actions and availability of repair facilities on system performance have been investigated. Higher availability of the components/equipments is inherently associated with their higher reliability and maintainability. The power generation system consists of five subsystems with four possible states: full working, reduced capacity, reduced efficiency and failed state. So, its availability should be carefully evaluated in order to foresee the performance of the power plant. The availability simulation model (Av. has been developed with the help of mathematical formulation based on Markov Birth-Death process using probabilistic approach. For this purpose, first differential equations have been generated. These equations are then solved using normalizing condition so as to determine the steady state availability of power generation system. In fact, availability analysis is very much effective in finding critical subsystems and deciding their preventive maintenance program for improving availability of the power plant as well as the power supply. From the graphs illustrated, the optimum values of failure/repair rates for maximum availability, of each subsystem is analyzed and then maintenance priorities are decided for all subsystems.The present paper highlights that in this system, Turbine governing subsystem is most sensitive demands more improvement in maintainability as compared to the other subsystems. While Turbine lubrication subsystem is least sensitive.
An autoregressive growth model for longitudinal item analysis.
Jeon, Minjeong; Rabe-Hesketh, Sophia
2016-09-01
A first-order autoregressive growth model is proposed for longitudinal binary item analysis where responses to the same items are conditionally dependent across time given the latent traits. Specifically, the item response probability for a given item at a given time depends on the latent trait as well as the response to the same item at the previous time, or the lagged response. An initial conditions problem arises because there is no lagged response at the initial time period. We handle this problem by adapting solutions proposed for dynamic models in panel data econometrics. Asymptotic and finite sample power for the autoregressive parameters are investigated. The consequences of ignoring local dependence and the initial conditions problem are also examined for data simulated from a first-order autoregressive growth model. The proposed methods are applied to longitudinal data on Korean students' self-esteem. PMID:26645083
Saloranta, Tuomo M; Armitage, James M; Haario, Heikki; Naes, Kristoffer; Cousins, Ian T; Barton, David N
2008-01-01
Multimedia environmental fate models are useful tools to investigate the long-term impacts of remediation measures designed to alleviate potential ecological and human health concerns in contaminated areas. Estimating and communicating the uncertainties associated with the model simulations is a critical task for demonstrating the transparency and reliability of the results. The Extended Fourier Amplitude Sensitivity Test(Extended FAST) method for sensitivity analysis and Bayesian Markov chain Monte Carlo (MCMC) method for uncertainty analysis and model calibration have several advantages over methods typically applied for multimedia environmental fate models. Most importantly, the simulation results and their uncertainties can be anchored to the available observations and their uncertainties. We apply these techniques for simulating the historical fate of polychlorinated dibenzo-p-dioxins and dibenzofurans (PCDD/Fs) in the Grenland fjords, Norway, and for predicting the effects of different contaminated sediment remediation (capping) scenarios on the future levels of PCDD/Fs in cod and crab therein. The remediation scenario simulations show that a significant remediation effect can first be seen when significant portions of the contaminated sediment areas are cleaned up, and that increase in capping area leads to both earlier achievement of good fjord status and narrower uncertainty in the predicted timing for this. PMID:18350897
Multivariate elliptically contoured autoregressive process
Taras Bodnar; Arjun K. Gupta
2014-01-01
In this paper, we introduce a new class of elliptically contoured processes. The suggested process possesses both the generality of the conditional heteroscedastic autoregressive process and the elliptical symmetry of the elliptically contoured distributions. In the empirical study we find the link between the conditional time varying behavior of the covariance matrix of the returns and the time variability of the investor’s coefficient of risk aversion. Moreover, it is shown that the non-dia...
Gregor, Karol; Danihelka, Ivo; Mnih, Andriy; Blundell, Charles; Wierstra, Daan
2013-01-01
We introduce a deep, generative autoencoder capable of learning hierarchies of distributed representations from data. Successive deep stochastic hidden layers are equipped with autoregressive connections, which enable the model to be sampled from quickly and exactly via ancestral sampling. We derive an efficient approximate parameter estimation method based on the minimum description length (MDL) principle, which can be seen as maximising a variational lower bound on the log-likelihood, with ...
Gaussian Processes for Functional Autoregression
Kowal, Daniel R.; David S. Matteson; Ruppert, David
2016-01-01
We develop a hierarchical Gaussian process model for forecasting and inference of functional time series data. Unlike existing methods, our approach is especially suited for sparsely or irregularly sampled curves and for curves sampled with non-negligible measurement error. The latent process is dynamically modeled as a functional autoregression (FAR) with Gaussian process innovations. We propose a fully nonparametric dynamic functional factor model for the dynamic innovation process, with br...
Dynamic temperature selection for parallel tempering in Markov chain Monte Carlo simulations
Vousden, W. D.; Farr, W. M.; Mandel, I.
2016-01-01
Modern problems in astronomical Bayesian inference require efficient methods for sampling from complex, high-dimensional, often multimodal probability distributions. Most popular methods, such as MCMC sampling, perform poorly on strongly multimodal probability distributions, rarely jumping between modes or settling on just one mode without finding others. Parallel tempering addresses this problem by sampling simultaneously with separate Markov chains from tempered versions of the target distribution with reduced contrast levels. Gaps between modes can be traversed at higher temperatures, while individual modes can be efficiently explored at lower temperatures. In this paper, we investigate how one might choose the ladder of temperatures to achieve more efficient sampling, as measured by the autocorrelation time of the sampler. In particular, we present a simple, easily implemented algorithm for dynamically adapting the temperature configuration of a sampler while sampling. This algorithm dynamically adjusts the temperature spacing to achieve a uniform rate of exchanges between chains at neighbouring temperatures. We compare the algorithm to conventional geometric temperature configurations on a number of test distributions and on an astrophysical inference problem, reporting efficiency gains by a factor of 1.2-2.5 over a well-chosen geometric temperature configuration and by a factor of 1.5-5 over a poorly chosen configuration. On all of these problems, a sampler using the dynamical adaptations to achieve uniform acceptance ratios between neighbouring chains outperforms one that does not.
Bracken, C. W.; Rajagopalan, B.; Zagona, E. A.
2011-12-01
Upper Colorado River Basin annual flow exhibits very low autocorrelation but regime shifting behavior causing long departures from the historical average flow producing sustained wet and dry periods. Traditional stochastic time series models do not capture this feature thereby misleading the water resources system risk and consequently impacting the management and planning efforts. To address this, we developed a nonstationary Hidden Markov (HM) model with Gamma component distributions, as opposed to Normal distributions which is widely used in literature, for stochastic simulation and short term forecasting. Global decoding from this model reveals and captures strong underlying persistent structure in the Lees Ferry flow time series. In addition to capturing the shifting mean, simulations from this model have a 20% greater chance than a first order Auto Regressive model (AR1), the best time series model for this data, of simulating wet and dry runs of 6 or more years. Relative to AR1 the HM model also captures the spectral features quite well. When applied to short term forecasting (i.e. of 1-2 years) they show higher skill relative to climatology but also to an AR1 model.
Lesage, James P.; Vance, Colin; Chih, Yao-Yu
2016-01-01
We apply a heterogenous coefficient spatial autoregressive panel model from Aquaro, Bailey and Pesaran (2015) to explore competition/cooperation by Berlin fueling stations in setting prices for diesel and E5 fuel. Unlike the maximum likelihood estimation method set forth by Aquaro, Bailey and Pesaran (2015), we rely on a Markov Chain Monte Carlo (MCMC) estimation methodology. MCMC estimates as applied here with non-informative priors will produce estimates equal to those from maximum likeliho...
A Note on Parameter Estimations of Panel Vector Autoregressive Models with Intercorrelation
Jian-hong Wu; Li-xing Zhu; Zai-xing Li
2009-01-01
This note considers parameter estimation for panel vector autoregressive models with intercorrela-tion. Conditional least squares estimators are derived and the asymptotic normality is established. A simulation is carried out for illustration.
Multivariate elliptically contoured autoregressive process
Taras Bodnar
2014-05-01
Full Text Available In this paper, we introduce a new class of elliptically contoured processes. The suggested process possesses both the generality of the conditional heteroscedastic autoregressive process and the elliptical symmetry of the elliptically contoured distributions. In the empirical study we find the link between the conditional time varying behavior of the covariance matrix of the returns and the time variability of the investor’s coefficient of risk aversion. Moreover, it is shown that the non-diagonal elements of the dispersion matrix are slowly varying in time.
Schoups, G.; Vrugt, J. A.; Fenicia, F.; van de Giesen, N. C.
2010-10-01
Conceptual rainfall-runoff models have traditionally been applied without paying much attention to numerical errors induced by temporal integration of water balance dynamics. Reliance on first-order, explicit, fixed-step integration methods leads to computationally cheap simulation models that are easy to implement. Computational speed is especially desirable for estimating parameter and predictive uncertainty using Markov chain Monte Carlo (MCMC) methods. Confirming earlier work of Kavetski et al. (2003), we show here that the computational speed of first-order, explicit, fixed-step integration methods comes at a cost: for a case study with a spatially lumped conceptual rainfall-runoff model, it introduces artificial bimodality in the marginal posterior parameter distributions, which is not present in numerically accurate implementations of the same model. The resulting effects on MCMC simulation include (1) inconsistent estimates of posterior parameter and predictive distributions, (2) poor performance and slow convergence of the MCMC algorithm, and (3) unreliable convergence diagnosis using the Gelman-Rubin statistic. We studied several alternative numerical implementations to remedy these problems, including various adaptive-step finite difference schemes and an operator splitting method. Our results show that adaptive-step, second-order methods, based on either explicit finite differencing or operator splitting with analytical integration, provide the best alternative for accurate and efficient MCMC simulation. Fixed-step or adaptive-step implicit methods may also be used for increased accuracy, but they cannot match the efficiency of adaptive-step explicit finite differencing or operator splitting. Of the latter two, explicit finite differencing is more generally applicable and is preferred if the individual hydrologic flux laws cannot be integrated analytically, as the splitting method then loses its advantage.
Rainfall data simulation by hidden Markov model and discrete wavelet transformation
Jayawardena, AW; Xu, PC; Li, WK
2009-01-01
In many regions, monthly (or bimonthly) rainfall data can be considered as deterministic while daily rainfall data may be treated as random. As a result, deterministic models may not sufficiently fit the daily data because of the strong stochastic nature, while stochastic models may also not reliably fit into daily rainfall time series because of the deterministic nature at the large scale (i.e. coarse scale). Although there are different approaches for simulating daily rainfall, mixing of de...
A stochastic Markov chain approach for tennis: Monte Carlo simulation and modeling
Aslam, Kamran
This dissertation describes the computational formulation of probability density functions (pdfs) that facilitate head-to-head match simulations in tennis along with ranking systems developed from their use. A background on the statistical method used to develop the pdfs , the Monte Carlo method, and the resulting rankings are included along with a discussion on ranking methods currently being used both in professional sports and in other applications. Using an analytical theory developed by Newton and Keller in [34] that defines a tennis player's probability of winning a game, set, match and single elimination tournament, a computational simulation has been developed in Matlab that allows further modeling not previously possible with the analytical theory alone. Such experimentation consists of the exploration of non-iid effects, considers the concept the varying importance of points in a match and allows an unlimited number of matches to be simulated between unlikely opponents. The results of these studies have provided pdfs that accurately model an individual tennis player's ability along with a realistic, fair and mathematically sound platform for ranking them.
Kepler AutoRegressive Planet Search: Motivation & Methodology
Caceres, Gabriel; Feigelson, Eric; Jogesh Babu, G.; Bahamonde, Natalia; Bertin, Karine; Christen, Alejandra; Curé, Michel; Meza, Cristian
2015-08-01
The Kepler AutoRegressive Planet Search (KARPS) project uses statistical methodology associated with autoregressive (AR) processes to model Kepler lightcurves in order to improve exoplanet transit detection in systems with high stellar variability. We also introduce a planet-search algorithm to detect transits in time-series residuals after application of the AR models. One of the main obstacles in detecting faint planetary transits is the intrinsic stellar variability of the host star. The variability displayed by many stars may have autoregressive properties, wherein later flux values are correlated with previous ones in some manner. Auto-Regressive Moving-Average (ARMA) models, Generalized Auto-Regressive Conditional Heteroskedasticity (GARCH), and related models are flexible, phenomenological methods used with great success to model stochastic temporal behaviors in many fields of study, particularly econometrics. Powerful statistical methods are implemented in the public statistical software environment R and its many packages. Modeling involves maximum likelihood fitting, model selection, and residual analysis. These techniques provide a useful framework to model stellar variability and are used in KARPS with the objective of reducing stellar noise to enhance opportunities to find as-yet-undiscovered planets. Our analysis procedure consisting of three steps: pre-processing of the data to remove discontinuities, gaps and outliers; ARMA-type model selection and fitting; and transit signal search of the residuals using a new Transit Comb Filter (TCF) that replaces traditional box-finding algorithms. We apply the procedures to simulated Kepler-like time series with known stellar and planetary signals to evaluate the effectiveness of the KARPS procedures. The ARMA-type modeling is effective at reducing stellar noise, but also reduces and transforms the transit signal into ingress/egress spikes. A periodogram based on the TCF is constructed to concentrate the signal
Autoregressive description of biological phenomena
Morariu, Vasile V; Pop, Alexadru; Soltuz, Stefan M; Buimaga-Iarinca, Luiza; Zainea, Oana
2008-01-01
Many natural phenomena can be described by power-laws. A closer look at various experimental data reveals more or less significant deviations from a 1/f spectrum. We exemplify such cases with phenomena offered by molecular biology, cell biophysics, and cognitive psychology. Some of these cases can be described by first order autoregressive (AR) models or by higher order AR models which are short range correlation models. The calculations are checked against astrophysical data which were fitted to a an AR model by a different method. We found that our fitting method of the data give similar results for the astrhophysical data and therefore applied the method for examples mentioned above. Our results show that such phenomena can be described by first or higher order of AR models. Therefore such examples are described by short range correlation properties while they can be easily confounded with long range correlation phenomena.
Weinberg, Martin D
2009-01-01
Computation of the marginal likelihood or "Bayesian Evidence" from a simulated posterior distribution is central to Bayesian model selection but is fraught with difficulty. The often-used harmonic mean approximation uses the posterior directly but is unstably sensitive to samples with anomalously small values of the likelihood and converges very slowly. The Laplace approximation is stable but makes strong, and often inappropriate, assumptions about the shape of the posterior distribution. It is useful, but not general. We need an algorithm that is general and easy to apply, like the harmonic mean approximation, but robust to sample size and multimodality. Here, I argue that the evidence can be stably computed from a posterior sample by careful attention to the numerics of the probability integral. Posing the expression for the Bayesian evidence as a Lebesgue integral, we may convert the evaluation of the sample statistic to a quadrature rule and show that the harmonic mean approximation suffers from enormous ...
Graphs: Associated Markov Chains
Murthy, Garimella Rama
2012-01-01
In this research paper, weighted / unweighted, directed / undirected graphs are associated with interesting Discrete Time Markov Chains (DTMCs) as well as Continuous Time Markov Chains (CTMCs). The equilibrium / transient behaviour of such Markov chains is studied. Also entropy dynamics (Shannon entropy) of certain structured Markov chains is investigated. Finally certain structured graphs and the associated Markov chains are studied.
We present a single-particle Lennard–Jones (L-J) model for CO2 and N2. Simplified L-J models for other small polyatomic molecules can be obtained following the methodology described herein. The phase-coexistence diagrams of single-component systems computed using the proposed single-particle models for CO2 and N2 agree well with experimental data over a wide range of temperatures. These diagrams are computed using the Markov Chain Monte Carlo method based on the Gibbs-NVT ensemble. This good agreement validates the proposed simplified models. That is, with properly selected parameters, the single-particle models have similar accuracy in predicting gas-phase properties as more complex, state-of-the-art molecular models. To further test these single-particle models, three binary mixtures of CH4, CO2 and N2 are studied using a Gibbs-NPT ensemble. These results are compared against experimental data over a wide range of pressures. The single-particle model has similar accuracy in the gas phase as traditional models although its deviation in the liquid phase is greater. Since the single-particle model reduces the particle number and avoids the time-consuming Ewald summation used to evaluate Coulomb interactions, the proposed model improves the computational efficiency significantly, particularly in the case of high liquid density where the acceptance rate of the particle-swap trial move increases. We compare, at constant temperature and pressure, the Gibbs-NPT and Gibbs-NVT ensembles to analyze their performance differences and results consistency. As theoretically predicted, the agreement between the simulations implies that Gibbs-NVT can be used to validate Gibbs-NPT predictions when experimental data is not available
Jadoon, K. Z.; Altaf, M. U.; McCabe, M. F.; Hoteit, I.; Moghadas, D.
2014-12-01
In arid and semi-arid regions, soil salinity has a major impact on agro-ecosystems, agricultural productivity, environment and sustainability. High levels of soil salinity adversely affect plant growth and productivity, soil and water quality, and may eventually result in soil erosion and land degradation. Being essentially a hazard, it's important to monitor and map soil salinity at an early stage to effectively use soil resources and maintain soil salinity level below the salt tolerance of crops. In this respect, low frequency electromagnetic induction (EMI) systems can be used as a noninvasive method to map the distribution of soil salinity at the field scale and at a high spatial resolution. In this contribution, an EMI system (the CMD Mini-Explorer) is used to estimate soil salinity using a Bayesian approach implemented via a Markov chain Monte Carlo (MCMC) sampling for inversion of multi-configuration EMI measurements. In-situ and EMI measurements were conducted across a farm where Acacia trees are irrigated with brackish water using a drip irrigation system. The electromagnetic forward model is based on the full solution of Maxwell's equation, and the subsurface is considered as a three-layer problem. In total, five parameters (electrical conductivity of three layers and thickness of top two layers) were inverted and modeled electrical conductivities were converted into the universal standard of soil salinity measurement (i.e. using the method of electrical conductivity of a saturated soil paste extract). Simulation results demonstrate that the proposed scheme successfully recovers soil salinity and reduces the uncertainties in the prior estimate. Analysis of the resulting posterior distribution of parameters indicates that electrical conductivity of the top two layers and the thickness of the first layer are well constrained by the EMI measurements. The proposed approach allows for quantitative mapping and monitoring of the spatial electrical conductivity
Li, Jun
2013-09-01
We present a single-particle Lennard-Jones (L-J) model for CO2 and N2. Simplified L-J models for other small polyatomic molecules can be obtained following the methodology described herein. The phase-coexistence diagrams of single-component systems computed using the proposed single-particle models for CO2 and N2 agree well with experimental data over a wide range of temperatures. These diagrams are computed using the Markov Chain Monte Carlo method based on the Gibbs-NVT ensemble. This good agreement validates the proposed simplified models. That is, with properly selected parameters, the single-particle models have similar accuracy in predicting gas-phase properties as more complex, state-of-the-art molecular models. To further test these single-particle models, three binary mixtures of CH4, CO2 and N2 are studied using a Gibbs-NPT ensemble. These results are compared against experimental data over a wide range of pressures. The single-particle model has similar accuracy in the gas phase as traditional models although its deviation in the liquid phase is greater. Since the single-particle model reduces the particle number and avoids the time-consuming Ewald summation used to evaluate Coulomb interactions, the proposed model improves the computational efficiency significantly, particularly in the case of high liquid density where the acceptance rate of the particle-swap trial move increases. We compare, at constant temperature and pressure, the Gibbs-NPT and Gibbs-NVT ensembles to analyze their performance differences and results consistency. As theoretically predicted, the agreement between the simulations implies that Gibbs-NVT can be used to validate Gibbs-NPT predictions when experimental data is not available. © 2013 Elsevier Inc.
Chow John L
2006-03-01
Full Text Available Abstract Background Management of acute respiratory distress syndrome (ARDS in the intensive care unit (ICU is clinically challenging and costly. Neuromuscular blocking agents may facilitate mechanical ventilation and improve oxygenation, but may result in prolonged recovery of neuromuscular function and acute quadriplegic myopathy syndrome (AQMS. The goal of this study was to address a hypothetical question via computer modeling: Would a reduction in intubation time of 6 hours and/or a reduction in the incidence of AQMS from 25% to 21%, provide enough benefit to justify a drug with an additional expenditure of $267 (the difference in acquisition cost between a generic and brand name neuromuscular blocker? Methods The base case was a 55 year-old man in the ICU with ARDS who receives neuromuscular blockade for 3.5 days. A Markov model was designed with hypothetical patients in 1 of 6 mutually exclusive health states: ICU-intubated, ICU-extubated, hospital ward, long-term care, home, or death, over a period of 6 months. The net monetary benefit was computed. Results Our computer simulation modeling predicted the mean cost for ARDS patients receiving standard care for 6 months to be $62,238 (5% – 95% percentiles $42,259 – $83,766, with an overall 6-month mortality of 39%. Assuming a ceiling ratio of $35,000, even if a drug (that cost $267 more hypothetically reduced AQMS from 25% to 21% and decreased intubation time by 6 hours, the net monetary benefit would only equal $137. Conclusion ARDS patients receiving a neuromuscular blocker have a high mortality, and unpredictable outcome, which results in large variability in costs per case. If a patient dies, there is no benefit to any drug that reduces ventilation time or AQMS incidence. A prospective, randomized pharmacoeconomic study of neuromuscular blockers in the ICU to asses AQMS or intubation times is impractical because of the highly variable clinical course of patients with ARDS.
Frank, T.D. [Center for the Ecological Study of Perception and Action, Department of Psychology, University of Connecticut, 406 Babbidge Road, Storrs, CT 06269 (United States)], E-mail: till.frank@uconn.edu
2008-06-16
Some elementary properties and examples of Markov processes are reviewed. It is shown that the definition of the Markov property naturally leads to a classification of Markov processes into linear and nonlinear ones.
Some elementary properties and examples of Markov processes are reviewed. It is shown that the definition of the Markov property naturally leads to a classification of Markov processes into linear and nonlinear ones
Single-Index Additive Vector Autoregressive Time Series Models
LI, YEHUA
2009-09-01
We study a new class of nonlinear autoregressive models for vector time series, where the current vector depends on single-indexes defined on the past lags and the effects of different lags have an additive form. A sufficient condition is provided for stationarity of such models. We also study estimation of the proposed model using P-splines, hypothesis testing, asymptotics, selection of the order of the autoregression and of the smoothing parameters and nonlinear forecasting. We perform simulation experiments to evaluate our model in various settings. We illustrate our methodology on a climate data set and show that our model provides more accurate yearly forecasts of the El Niño phenomenon, the unusual warming of water in the Pacific Ocean. © 2009 Board of the Foundation of the Scandinavian Journal of Statistics.
Nonlinear autoregressive models and long memory
Kapetanios, George
2004-01-01
This note shows that regime switching nonlinear autoregressive models widely used in the time series literature can exhibit arbitrary degrees of long memory via appropriate definition of the model regimes.
Confidence Intervals for Autoregressive Coefficients Near One
Elliott, Graham; Stock, James H.
2000-01-01
Often we are interested in the largest root of an autoregressive process. Available methods rely on inverting t-tests to obtain confidence intervals. However, for large autoregressive roots, t-tests do not approximate asymptotically uniformly most powerful tests and do not have optimality properties when inverted for confidence intervals. We exploit the relationship between the power of tests and accuracy of confidence intervals, and suggest methods which are asymptotically more accurate than...
This paper proposes a comprehensive framework for accelerating population balance-Monte Carlo (PBMC) simulation of particle coagulation dynamics. By combining Markov jump model, weighted majorant kernel and GPU (graphics processing unit) parallel computing, a significant gain in computational efficiency is achieved. The Markov jump model constructs a coagulation-rule matrix of differentially-weighted simulation particles, so as to capture the time evolution of particle size distribution with low statistical noise over the full size range and as far as possible to reduce the number of time loopings. Here three coagulation rules are highlighted and it is found that constructing appropriate coagulation rule provides a route to attain the compromise between accuracy and cost of PBMC methods. Further, in order to avoid double looping over all simulation particles when considering the two-particle events (typically, particle coagulation), the weighted majorant kernel is introduced to estimate the maximum coagulation rates being used for acceptance–rejection processes by single-looping over all particles, and meanwhile the mean time-step of coagulation event is estimated by summing the coagulation kernels of rejected and accepted particle pairs. The computational load of these fast differentially-weighted PBMC simulations (based on the Markov jump model) is reduced greatly to be proportional to the number of simulation particles in a zero-dimensional system (single cell). Finally, for a spatially inhomogeneous multi-dimensional (multi-cell) simulation, the proposed fast PBMC is performed in each cell, and multiple cells are parallel processed by multi-cores on a GPU that can implement the massively threaded data-parallel tasks to obtain remarkable speedup ratio (comparing with CPU computation, the speedup ratio of GPU parallel computing is as high as 200 in a case of 100 cells with 10 000 simulation particles per cell). These accelerating approaches of PBMC are
Xu, Zuwei; Zhao, Haibo, E-mail: klinsmannzhb@163.com; Zheng, Chuguang
2015-01-15
This paper proposes a comprehensive framework for accelerating population balance-Monte Carlo (PBMC) simulation of particle coagulation dynamics. By combining Markov jump model, weighted majorant kernel and GPU (graphics processing unit) parallel computing, a significant gain in computational efficiency is achieved. The Markov jump model constructs a coagulation-rule matrix of differentially-weighted simulation particles, so as to capture the time evolution of particle size distribution with low statistical noise over the full size range and as far as possible to reduce the number of time loopings. Here three coagulation rules are highlighted and it is found that constructing appropriate coagulation rule provides a route to attain the compromise between accuracy and cost of PBMC methods. Further, in order to avoid double looping over all simulation particles when considering the two-particle events (typically, particle coagulation), the weighted majorant kernel is introduced to estimate the maximum coagulation rates being used for acceptance–rejection processes by single-looping over all particles, and meanwhile the mean time-step of coagulation event is estimated by summing the coagulation kernels of rejected and accepted particle pairs. The computational load of these fast differentially-weighted PBMC simulations (based on the Markov jump model) is reduced greatly to be proportional to the number of simulation particles in a zero-dimensional system (single cell). Finally, for a spatially inhomogeneous multi-dimensional (multi-cell) simulation, the proposed fast PBMC is performed in each cell, and multiple cells are parallel processed by multi-cores on a GPU that can implement the massively threaded data-parallel tasks to obtain remarkable speedup ratio (comparing with CPU computation, the speedup ratio of GPU parallel computing is as high as 200 in a case of 100 cells with 10 000 simulation particles per cell). These accelerating approaches of PBMC are
Katsuhiro Sugita
2015-01-01
In this paper we analyze the predictive power of the yield curve on output growth using a vector autoregressive model with multiple structural breaks in the intercept term and the volatility. To estimate the model and to detect the number of breaks, we apply a Bayesian approach with Markov chain Monte Carlo algorithm. We find strong evidence of three structural breaks using the US data.
Hidaka, Shohei
2015-01-01
A Markov process, which is constructed recursively, arises in stochastic games with Markov strategies. In this study, we defined a special class of random processes called the recursive Markov process, which has infinitely many states but can be expressed in a closed form. We derive the characteristic equation which the marginal stationary distribution of an arbitrary recursive Markov process needs to satisfy.
A model of consecutive-k-out-of-n: F repairable system with non-exponential repair time distribution and (k-1)-step Markov dependence is introduced in this paper along with algorithms of three Monte Carlo methods, i.e. importance sampling, conditional expectation estimation and combination of the two methods, to estimate dependability of the non-Markov model including reliability, transient unavailability, MTTF, and MTBF. A numerical example is presented to demonstrate the efficiencies of above methods. The results show that combinational method has the highest efficiency for estimation of unreliability and unavailability, while conditional expectation estimation is the most efficient method for estimation of MTTF and MTBF. Conditional expectation estimation seems to have overall higher speedups in estimating dependability of such systems
Markov processes and controlled Markov chains
Filar, Jerzy; Chen, Anyue
2002-01-01
The general theory of stochastic processes and the more specialized theory of Markov processes evolved enormously in the second half of the last century. In parallel, the theory of controlled Markov chains (or Markov decision processes) was being pioneered by control engineers and operations researchers. Researchers in Markov processes and controlled Markov chains have been, for a long time, aware of the synergies between these two subject areas. However, this may be the first volume dedicated to highlighting these synergies and, almost certainly, it is the first volume that emphasizes the contributions of the vibrant and growing Chinese school of probability. The chapters that appear in this book reflect both the maturity and the vitality of modern day Markov processes and controlled Markov chains. They also will provide an opportunity to trace the connections that have emerged between the work done by members of the Chinese school of probability and the work done by the European, US, Central and South Ameri...
Discrete Quantum Markov Chains
Faigle, Ulrich
2010-01-01
A framework for finite-dimensional quantum Markov chains on Hilbert spaces is introduced. Quantum Markov chains generalize both classical Markov chains with possibly hidden states and existing models of quantum walks on finite graphs. Quantum Markov chains are based on Markov operations that may be applied to quantum systems and include quantum measurements, for example. It is proved that quantum Markov chains are asymptotically stationary and hence possess ergodic and entropic properties. With a quantum Markov chain one may associate a quantum Markov process, which is a stochastic process in the classical sense. Generalized Markov chains allow a representation with respect to a generalized Markov source model with definite (but possibly hidden) states relative to which observables give rise to classical stochastic processes. It is demonstrated that this model allows for observables to violate Bell's inequality.
Jalayer, Fatemeh; Ebrahimian, Hossein
2014-05-01
Introduction The first few days elapsed after the occurrence of a strong earthquake and in the presence of an ongoing aftershock sequence are quite critical for emergency decision-making purposes. Epidemic Type Aftershock Sequence (ETAS) models are used frequently for forecasting the spatio-temporal evolution of seismicity in the short-term (Ogata, 1988). The ETAS models are epidemic stochastic point process models in which every earthquake is a potential triggering event for subsequent earthquakes. The ETAS model parameters are usually calibrated a priori and based on a set of events that do not belong to the on-going seismic sequence (Marzocchi and Lombardi 2009). However, adaptive model parameter estimation, based on the events in the on-going sequence, may have several advantages such as, tuning the model to the specific sequence characteristics, and capturing possible variations in time of the model parameters. Simulation-based methods can be employed in order to provide a robust estimate for the spatio-temporal seismicity forecasts in a prescribed forecasting time interval (i.e., a day) within a post-main shock environment. This robust estimate takes into account the uncertainty in the model parameters expressed as the posterior joint probability distribution for the model parameters conditioned on the events that have already occurred (i.e., before the beginning of the forecasting interval) in the on-going seismic sequence. The Markov Chain Monte Carlo simulation scheme is used herein in order to sample directly from the posterior probability distribution for ETAS model parameters. Moreover, the sequence of events that is going to occur during the forecasting interval (and hence affecting the seismicity in an epidemic type model like ETAS) is also generated through a stochastic procedure. The procedure leads to two spatio-temporal outcomes: (1) the probability distribution for the forecasted number of events, and (2) the uncertainty in estimating the
Accurate determination of thermodynamic properties of petroleum reservoir fluids is of great interest to many applications, especially in petroleum engineering and chemical engineering. Molecular simulation has many appealing features, especially its requirement of fewer tuned parameters but yet better predicting capability; however it is well known that molecular simulation is very CPU expensive, as compared to equation of state approaches. We have recently introduced an efficient thermodynamically consistent technique to regenerate rapidly Monte Carlo Markov Chains (MCMCs) at different thermodynamic conditions from the existing data points that have been pre-computed with expensive classical simulation. This technique can speed up the simulation more than a million times, making the regenerated molecular simulation almost as fast as equation of state approaches. In this paper, this technique is first briefly reviewed and then numerically investigated in its capability of predicting ensemble averages of primary quantities at different neighboring thermodynamic conditions to the original simulated MCMCs. Moreover, this extrapolation technique is extended to predict second derivative properties (e.g. heat capacity and fluid compressibility). The method works by reweighting and reconstructing generated MCMCs in canonical ensemble for Lennard-Jones particles. In this paper, system's potential energy, pressure, isochoric heat capacity and isothermal compressibility along isochors, isotherms and paths of changing temperature and density from the original simulated points were extrapolated. Finally, an optimized set of Lennard-Jones parameters (ε, σ) for single site models were proposed for methane, nitrogen and carbon monoxide
Kadoura, Ahmad; Sun, Shuyu; Salama, Amgad
2014-08-01
Accurate determination of thermodynamic properties of petroleum reservoir fluids is of great interest to many applications, especially in petroleum engineering and chemical engineering. Molecular simulation has many appealing features, especially its requirement of fewer tuned parameters but yet better predicting capability; however it is well known that molecular simulation is very CPU expensive, as compared to equation of state approaches. We have recently introduced an efficient thermodynamically consistent technique to regenerate rapidly Monte Carlo Markov Chains (MCMCs) at different thermodynamic conditions from the existing data points that have been pre-computed with expensive classical simulation. This technique can speed up the simulation more than a million times, making the regenerated molecular simulation almost as fast as equation of state approaches. In this paper, this technique is first briefly reviewed and then numerically investigated in its capability of predicting ensemble averages of primary quantities at different neighboring thermodynamic conditions to the original simulated MCMCs. Moreover, this extrapolation technique is extended to predict second derivative properties (e.g. heat capacity and fluid compressibility). The method works by reweighting and reconstructing generated MCMCs in canonical ensemble for Lennard-Jones particles. In this paper, system's potential energy, pressure, isochoric heat capacity and isothermal compressibility along isochors, isotherms and paths of changing temperature and density from the original simulated points were extrapolated. Finally, an optimized set of Lennard-Jones parameters (ε, σ) for single site models were proposed for methane, nitrogen and carbon monoxide.
Kadoura, Ahmad Salim
2014-08-01
Accurate determination of thermodynamic properties of petroleum reservoir fluids is of great interest to many applications, especially in petroleum engineering and chemical engineering. Molecular simulation has many appealing features, especially its requirement of fewer tuned parameters but yet better predicting capability; however it is well known that molecular simulation is very CPU expensive, as compared to equation of state approaches. We have recently introduced an efficient thermodynamically consistent technique to regenerate rapidly Monte Carlo Markov Chains (MCMCs) at different thermodynamic conditions from the existing data points that have been pre-computed with expensive classical simulation. This technique can speed up the simulation more than a million times, making the regenerated molecular simulation almost as fast as equation of state approaches. In this paper, this technique is first briefly reviewed and then numerically investigated in its capability of predicting ensemble averages of primary quantities at different neighboring thermodynamic conditions to the original simulated MCMCs. Moreover, this extrapolation technique is extended to predict second derivative properties (e.g. heat capacity and fluid compressibility). The method works by reweighting and reconstructing generated MCMCs in canonical ensemble for Lennard-Jones particles. In this paper, system\\'s potential energy, pressure, isochoric heat capacity and isothermal compressibility along isochors, isotherms and paths of changing temperature and density from the original simulated points were extrapolated. Finally, an optimized set of Lennard-Jones parameters (ε, σ) for single site models were proposed for methane, nitrogen and carbon monoxide. © 2014 Elsevier Inc.
Testing the Markov condition in ion channel recordings
Timmer, J
1997-01-01
A statistical test is presented to decide whether data are adequately described by probabilistic functions of finite state Markov chains (''hidden Markov models'') as applied in the analysis of ion channel data. Particularly, the test can be used to decide whether a system obeys the Markov condition. Simulation studies are performed in order to investigate the sensitivity of the proposed test against violations of the model assumptions. The test can be applied analogously to Markov models.
Oracle Inequalities for High Dimensional Vector Autoregressions
Callot, Laurent; Kock, Anders Bredahl
This paper establishes non-asymptotic oracle inequalities for the prediction error and estimation accuracy of the LASSO in stationary vector autoregressive models. These inequalities are used to establish consistency of the LASSO even when the number of parameters is of a much larger order of...... hence the correct sparsity pattern). Finally conditions under which the Adaptive LASSO reveals the correct sign pattern with probability tending to one are given. Again, the number of parameters may be much larger than the sample size. Some maximal inequalities for vector autoregressions which might be...
Non-linear autoregressive Markov regime-switching models are intuitive. Time-series approaches for the modelling of electricity spot prices are frequently proposed. In this paper, such models are compared with an ordinary linear autoregressive model with regard to their forecast performances. The study is carried out using German daily spot-prices from the European Energy Exchange in Leipzig. Four non-linear models are used for the forecast study. The results of the study suggest that Markov regime-switching models provide better forecasts than linear models. (author)
Nonuniform Markov Geometric Measures
Neunhäuserer, J.
2015-01-01
We generalize results of Fan and Zhang [6] on absolute continuity and singularity of the golden Markov geometric series to nonuniform stochastic series given by arbitrary Markov process. In addition we describe an application of these results in fractal geometry.
Cardiac arrhythmia classification using autoregressive modeling
Srinivasan Narayanan; Ge Dingfei; Krishnan Shankar M
2002-01-01
Abstract Background Computer-assisted arrhythmia recognition is critical for the management of cardiac disorders. Various techniques have been utilized to classify arrhythmias. Generally, these techniques classify two or three arrhythmias or have significantly large processing times. A simpler autoregressive modeling (AR) technique is proposed to classify normal sinus rhythm (NSR) and various cardiac arrhythmias including atrial premature contraction (APC), premature ventricular contraction (...
The Integration Order of Vector Autoregressive Processes
Franchi, Massimo
We show that the order of integration of a vector autoregressive process is equal to the difference between the multiplicity of the unit root in the characteristic equation and the multiplicity of the unit root in the adjoint matrix polynomial. The equivalence with the standard I(1) and I(2...
Quantum Markov fields on graphs
Accardi, Luigi; Ohno, Hiromichi; Mukhamedov, Farrukh
2009-01-01
We introduce generalized quantum Markov states and generalized d-Markov chains which extend the notion quantum Markov chains on spin systems to that on $C^*$-algebras defined by general graphs. As examples of generalized d-Markov chains, we construct the entangled Markov fields on tree graphs. The concrete examples of generalized d-Markov chains on Cayley trees are also investigated.
Kianoush Fathi Vajargah
2015-01-01
Full Text Available An available method of modeling and predicting the economic time series is the use of stochastic differential equations, which are often determined as jump-diffusion stochastic differential equations in financial markets and underlier economic dynamics. Besides the diffusion term that is a geometric Brownian model with Wiener random process, these equations contain a jump term that follows Poisson process and depends on the type of market. This study presented two different models based on a certain class of jump-diffusion stochastic differential equations with random fluctuations: Black- Scholes model and Merton model (1976, including jump-diffusion (JD model, which were compared, and their parameters and hidden variables were evaluated using Markov chain Monte Carlo (MCMC method.
Monaco, James Peter; Madabhushi, Anant
2011-07-01
The ability of classification systems to adjust their performance (sensitivity/specificity) is essential for tasks in which certain errors are more significant than others. For example, mislabeling cancerous lesions as benign is typically more detrimental than mislabeling benign lesions as cancerous. Unfortunately, methods for modifying the performance of Markov random field (MRF) based classifiers are noticeably absent from the literature, and thus most such systems restrict their performance to a single, static operating point (a paired sensitivity/specificity). To address this deficiency we present weighted maximum posterior marginals (WMPM) estimation, an extension of maximum posterior marginals (MPM) estimation. Whereas the MPM cost function penalizes each error equally, the WMPM cost function allows misclassifications associated with certain classes to be weighted more heavily than others. This creates a preference for specific classes, and consequently a means for adjusting classifier performance. Realizing WMPM estimation (like MPM estimation) requires estimates of the posterior marginal distributions. The most prevalent means for estimating these--proposed by Marroquin--utilizes a Markov chain Monte Carlo (MCMC) method. Though Marroquin's method (M-MCMC) yields estimates that are sufficiently accurate for MPM estimation, they are inadequate for WMPM. To more accurately estimate the posterior marginals we present an equally simple, but more effective extension of the MCMC method (E-MCMC). Assuming an identical number of iterations, E-MCMC as compared to M-MCMC yields estimates with higher fidelity, thereby 1) allowing a far greater number and diversity of operating points and 2) improving overall classifier performance. To illustrate the utility of WMPM and compare the efficacies of M-MCMC and E-MCMC, we integrate them into our MRF-based classification system for detecting cancerous glands in (whole-mount or quarter) histological sections of the prostate
Kevin McNally
2012-01-01
Full Text Available There are numerous biomonitoring programs, both recent and ongoing, to evaluate environmental exposure of humans to chemicals. Due to the lack of exposure and kinetic data, the correlation of biomarker levels with exposure concentrations leads to difficulty in utilizing biomonitoring data for biological guidance values. Exposure reconstruction or reverse dosimetry is the retrospective interpretation of external exposure consistent with biomonitoring data. We investigated the integration of physiologically based pharmacokinetic modelling, global sensitivity analysis, Bayesian inference, and Markov chain Monte Carlo simulation to obtain a population estimate of inhalation exposure to m-xylene. We used exhaled breath and venous blood m-xylene and urinary 3-methylhippuric acid measurements from a controlled human volunteer study in order to evaluate the ability of our computational framework to predict known inhalation exposures. We also investigated the importance of model structure and dimensionality with respect to its ability to reconstruct exposure.
Dynkin, E B
1960-01-01
Theory of Markov Processes provides information pertinent to the logical foundations of the theory of Markov random processes. This book discusses the properties of the trajectories of Markov processes and their infinitesimal operators.Organized into six chapters, this book begins with an overview of the necessary concepts and theorems from measure theory. This text then provides a general definition of Markov process and investigates the operations that make possible an inspection of the class of Markov processes corresponding to a given transition function. Other chapters consider the more c
Context Tree Estimation in Variable Length Hidden Markov Models
Dumont, Thierry
2011-01-01
We address the issue of context tree estimation in variable length hidden Markov models. We propose an estimator of the context tree of the hidden Markov process which needs no prior upper bound on the depth of the context tree. We prove that the estimator is strongly consistent. This uses information-theoretic mixture inequalities in the spirit of Finesso and Lorenzo(Consistent estimation of the order for Markov and hidden Markov chains(1990)) and E.Gassiat and S.Boucheron (Optimal error exponents in hidden Markov model order estimation(2003)). We propose an algorithm to efficiently compute the estimator and provide simulation studies to support our result.
J. A. Vrugt
2011-04-01
Full Text Available Formal and informal Bayesian approaches are increasingly being used to treat forcing, model structural, parameter and calibration data uncertainty, and summarize hydrologic prediction uncertainty. This requires posterior sampling methods that approximate the (evolving posterior distribution. We recently introduced the DiffeRential Evolution Adaptive Metropolis (DREAM algorithm, an adaptive Markov Chain Monte Carlo (MCMC method that is especially designed to solve complex, high-dimensional and multimodal posterior probability density functions. The method runs multiple chains in parallel, and maintains detailed balance and ergodicity. Here, I present the latest algorithmic developments, and introduce a discrete sampling variant of DREAM that samples the parameter space at fixed points. The development of this new code, DREAM(D, has been inspired by the existing class of integer optimization problems, and emerging class of experimental design problems. Such non-continuous parameter estimation problems are of considerable theoretical and practical interest. The theory developed herein is applicable to DREAM(ZS (Vrugt et al., 2011 and MT-DREAM(ZS (Laloy and Vrugt, 2011 as well. Two case studies involving a sudoku puzzle and rainfall – runoff model calibration problem are used to illustrate DREAM(D.
Order 1 autoregressive process of finite length
Vamos, Calin; Craciun, Maria
2007-01-01
The stochastic processes of finite length defined by recurrence relations request additional relations specifying the first terms of the process analogously to the initial conditions for the differential equations. As a general rule, in time series theory one analyzes only stochastic processes of infinite length which need no such initial conditions and their properties are less difficult to be determined. In this paper we compare the properties of the order 1 autoregressive processes of finite and infinite length and we prove that the time series length has an important influence mainly if the serial correlation is significant. These different properties can manifest themselves as transient effects produced when a time series is numerically generated. We show that for an order 1 autoregressive process the transient behavior can be avoided if the first term is a Gaussian random variable with standard deviation equal to that of the theoretical infinite process and not to that of the white noise innovation.
Generalization of Brownian Motion with Autoregressive Increments
Fendick, Kerry
2011-01-01
This paper introduces a generalization of Brownian motion with continuous sample paths and stationary, autoregressive increments. This process, which we call a Brownian ray with drift, is characterized by three parameters quantifying distinct effects of drift, volatility, and autoregressiveness. A Brownian ray with drift, conditioned on its state at the beginning of an interval, is another Brownian ray with drift over the interval, and its expected path over the interval is a ray with a slope that depends on the conditioned state. This paper shows how Brownian rays can be applied in finance for the analysis of queues or inventories and the valuation of options. We model a queue's net input process as a superposition of Brownian rays with drift and derive the transient distribution of the queue length conditional on past queue lengths and on past states of the individual Brownian rays comprising the superposition. The transient distributions of Regulated Brownian Motion and of the Regulated Brownian Bridge are...
Markov chains analytic and Monte Carlo computations
Graham, Carl
2014-01-01
Markov Chains: Analytic and Monte Carlo Computations introduces the main notions related to Markov chains and provides explanations on how to characterize, simulate, and recognize them. Starting with basic notions, this book leads progressively to advanced and recent topics in the field, allowing the reader to master the main aspects of the classical theory. This book also features: Numerous exercises with solutions as well as extended case studies.A detailed and rigorous presentation of Markov chains with discrete time and state space.An appendix presenting probabilistic notions that are nec
Some correlation properties of spatial autoregressions
Martellosio, Federico
2009-01-01
This paper investigates how the correlations implied by a first-order simultaneous autoregressive (SAR(1)) process are affected by the weights matrix and the autocorrelation parameter. An interpretation of the covariance structure of the process is provided, based on the walks connecting the spatial units. The interpretation serves to explain a number of correlation properties of SAR(1) processes, and clarifies why in practical applications it is difficult, or even impossible, to use SAR(1) p...
Knuiman Matthew
2008-06-01
Full Text Available Abstract Background Treatments for coronary heart disease (CHD have evolved rapidly over the last 15 years with considerable change in the number and effectiveness of both medical and surgical treatments. This period has seen the rapid development and uptake of statin drugs and coronary artery revascularization procedures (CARPs that include Coronary Artery Bypass Graft procedures (CABGs and Percutaneous Coronary Interventions (PCIs. It is difficult in an era of such rapid change to accurately forecast requirements for treatment services such as CARPs. In a previous paper we have described and outlined the use of a Markov Monte Carlo simulation model for analyzing and predicting the requirements for CARPs for the population of Western Australia (Mannan et al, 2007. In this paper, we expand on the use of this model for forecasting CARPs in Western Australia with a focus on the lack of adequate performance of the (standard model for forecasting CARPs in a period during the mid 1990s when there were considerable changes to CARP technology and implementation policy and an exploration and demonstration of how the standard model may be adapted to achieve better performance. Methods Selected key CARP event model probabilities are modified based on information relating to changes in the effectiveness of CARPs from clinical trial evidence and an awareness of trends in policy and practice of CARPs. These modified model probabilities and the ones obtained by standard methods are used as inputs in our Markov simulation model. Results The projected numbers of CARPs in the population of Western Australia over 1995–99 only improve marginally when modifications to model probabilities are made to incorporate an increase in effectiveness of PCI procedures. However, the projected numbers improve substantially when, in addition, further modifications are incorporated that relate to the increased probability of a PCI procedure and the reduced probability of a CABG
Saldanha Filho, Paulo Carlos
1998-02-01
Stochastic simulation has been employed in petroleum reservoir characterization as a modeling tool able to reconcile information from several different sources. It has the ability to preserve the variability of the modeled phenomena and permits transference of geological knowledge to numerical models of flux, whose predictions on reservoir constitute the main basis for reservoir management decisions. Several stochastic models have been used and/or suggested, depending on the nature of the phenomena to be described. Markov Random Fields (MRFs) appear as an alternative for the modeling of discrete variables, mainly reservoirs with mosaic architecture of facies. In this dissertation, the reader is introduced to the stochastic modeling by MRFs in a generic sense. The main aspects of the technique are reviewed. MRF Conceptual Background is described: its characterization through the Markovian property and the equivalence to Gibbs distributions. The framework for generic modeling of MRFs is described. The classical models of Ising and Potts-Strauss are specific in this context and are related to models of Ising and Potts-Strauss are specific in this context and are related to models used in petroleum reservoir characterization. The problem of parameter estimation is discussed. The maximum pseudolikelihood estimators for some models are presented. Estimators for two models useful for reservoir characterization are developed, and represent a new contribution to the subject. Five algorithms for the Conditional Simulation of MRFs are described: the Metropolis algorithm, the algorithm of German and German (Gibbs sampler), the algorithm of Swendsen-Wang, the algorithm of Wolff, and the algorithm of Flinn. Finally, examples of simulation for some of the models discussed are presented, along with their implications on the modelling of petroleum reservoirs. (author)
Modeling of non-stationary autoregressive alpha-stable processe
National Aeronautics and Space Administration — In the literature, impulsive signals are mostly modeled by symmetric alpha-stable processes. To represent their temporal dependencies, usually autoregressive models...
Multiple phase derivative estimation using autoregressive modeling in holographic interferometry
A novel technique is proposed for the direct and simultaneous estimation of multiple phase derivatives from a deformation modulated carrier fringe pattern in a multi-wave holographic interferometry set-up. The fringe intensity is represented as a spatially-varying autoregressive (SVAR) model. The spatially-varying coefficients of the SVAR model are derived using a forward–backward approach of linear estimation of the fringe intensity. Using these coefficients, the poles of the SVAR model transfer function are computed and the angles of these poles provide the estimation of phase derivatives. The estimation of carrier frequency is performed by the proposed method using a reference interferogram. Simulation results are provided in the presence of noise and fringe amplitude modulation. (paper)
Justesen, Jørn
2005-01-01
A simple construction of two-dimensional (2-D) fields is presented. Rows and columns are outcomes of the same Markov chain. The entropy can be calculated explicitly.......A simple construction of two-dimensional (2-D) fields is presented. Rows and columns are outcomes of the same Markov chain. The entropy can be calculated explicitly....
Li, Chunjian; Andersen, Søren Vang
2007-01-01
We propose two blind system identification methods that exploit the underlying dynamics of non-Gaussian signals. The two signal models to be identified are: an Auto-Regressive (AR) model driven by a discrete-state Hidden Markov process, and the same model whose output is perturbed by white Gaussian...... iterative schemes. The proposed methods also enjoy good data efficiency since only second order statistics is involved in the computation. When measurement noise is present, a novel Switching Kalman Smoother is incorporated into the EM algorithm, obtaining optimum nonlinear MMSE estimates of the system...
Badawi A
2012-04-01
Full Text Available Soroush Mortaz*, Christine Wessman*, Ross Duncan, Rachel Gray, Alaa Badawi Office of Biotechnology Genomics and Population Health, Public Health Agency of Canada, Toronto, Ontario, Canada*Both authors contributed equally to this workBackground: Type 2 diabetes mellitus (T2DM is a major global health problem. An estimated 20%–50% of diabetic subjects in Canada are currently undiagnosed, and around 20%–30% have already developed complications. Screening for high blood glucose levels can identify people with prediabetic conditions and permit introduction of timely and effective prevention. This study examines the benefit of screening for impaired fasting glucose (IFG and T2DM. If intervention is introduced at this prediabetic stage, it can be most effective in delaying the onset and complications of T2DM.Methods: Using a Markov model simulation, we compare the cost-effectiveness of screening for prediabetes (IFG and T2DM with the strategy of no screening. An initial cohort of normoglycemic, prediabetic, or undiagnosed diabetic adults with one or more T2DM risk factors was used to model the strategies mentioned over a 10-year period. Subjects without known prediabetes or diabetes are screened every 3 years and persons with prediabetes were tested for diabetes on an annual basis. The model weighs the increase in quality-adjusted life-years (QALYs associated with early detection of prediabetes and earlier diagnosis of T2DM due to lifestyle intervention and early treatment in asymptomatic subjects.Results: Costs for each QALY gained were $2281 for conventional screening compared with $2890 for no screening. Thus, in this base-case analysis, conventional screening with a frequency of once every 3 years was favored over no screening. Furthermore, conventional screening was more favorable compared with no screening over a wide range of willingness-to-pay thresholds. Changing the frequency of screening did not affect the overall results. Screening
A General Representation Theorem for Integrated Vector Autoregressive Processes
Franchi, Massimo
We study the algebraic structure of an I(d) vector autoregressive process, where d is restricted to be an integer. This is useful to characterize its polynomial cointegrating relations and its moving average representation, that is to prove a version of the Granger representation theorem valid...... for I(d) vector autoregressive processes...
Markov chain Monte Carlo test of toric homogeneous Markov chains
Takemura, Akimichi; Hara, Hisayuki
2010-01-01
Markov chain models are used in various fields, such behavioral sciences or econometrics. Although the goodness of fit of the model is usually assessed by large sample approximation, it is desirable to use conditional tests if the sample size is not large. We study Markov bases for performing conditional tests of the toric homogeneous Markov chain model, which is the envelope exponential family for the usual homogeneous Markov chain model. We give a complete description of a Markov basis for ...
Semi-Markov Arnason-Schwarz models.
King, Ruth; Langrock, Roland
2016-06-01
We consider multi-state capture-recapture-recovery data where observed individuals are recorded in a set of possible discrete states. Traditionally, the Arnason-Schwarz model has been fitted to such data where the state process is modeled as a first-order Markov chain, though second-order models have also been proposed and fitted to data. However, low-order Markov models may not accurately represent the underlying biology. For example, specifying a (time-independent) first-order Markov process involves the assumption that the dwell time in each state (i.e., the duration of a stay in a given state) has a geometric distribution, and hence that the modal dwell time is one. Specifying time-dependent or higher-order processes provides additional flexibility, but at the expense of a potentially significant number of additional model parameters. We extend the Arnason-Schwarz model by specifying a semi-Markov model for the state process, where the dwell-time distribution is specified more generally, using, for example, a shifted Poisson or negative binomial distribution. A state expansion technique is applied in order to represent the resulting semi-Markov Arnason-Schwarz model in terms of a simpler and computationally tractable hidden Markov model. Semi-Markov Arnason-Schwarz models come with only a very modest increase in the number of parameters, yet permit a significantly more flexible state process. Model selection can be performed using standard procedures, and in particular via the use of information criteria. The semi-Markov approach allows for important biological inference to be drawn on the underlying state process, for example, on the times spent in the different states. The feasibility of the approach is demonstrated in a simulation study, before being applied to real data corresponding to house finches where the states correspond to the presence or absence of conjunctivitis. PMID:26584064
Rates of convergence of some multivariate Markov chains with polynomial eigenfunctions
Khare, Kshitij; 10.1214/08-AAP562
2009-01-01
We provide a sharp nonasymptotic analysis of the rates of convergence for some standard multivariate Markov chains using spectral techniques. All chains under consideration have multivariate orthogonal polynomial as eigenfunctions. Our examples include the Moran model in population genetics and its variants in community ecology, the Dirichlet-multinomial Gibbs sampler, a class of generalized Bernoulli--Laplace processes, a generalized Ehrenfest urn model and the multivariate normal autoregressive process.
Windisch, Tobias
2015-01-01
The mixing behaviour of Markov chains on lattice points of polytopes using Markov bases is examined. It is shown that, in fixed dimension, these Markov chains do not mix rapidly. As a way out, a method of how to adapt Markov bases in order to achieve the fastest mixing behaviour is introduced.
Fuzzy Markov chains: uncertain probabilities
James J. Buckley; Eslami, Esfandiar
2002-01-01
We consider finite Markov chains where there are uncertainties in some of the transition probabilities. These uncertainties are modeled by fuzzy numbers. Using a restricted fuzzy matrix multiplication we investigate the properties of regular, and absorbing, fuzzy Markov chains and show that the basic properties of these classical Markov chains generalize to fuzzy Markov chains.
Yu Zhao
2013-01-01
Full Text Available In the study, we discussed the generalized autoregressive conditional heteroskedasticity model and enhanced it with wavelet transform to evaluate the daily returns for 1/4/2002-30/12/2011 period in Brent oil market. We proposed discrete wavelet transform generalized autoregressive conditional heteroskedasticity model to increase the forecasting performance of the generalized autoregressive conditional heteroskedasticity model. Our new approach can overcome the defect of generalized autoregressive conditional heteroskedasticity family models which can’t describe the detail and partial features of times series and retain the advantages of them at the same time. Comparing with the generalized autoregressive conditional heteroskedasticity model, the new approach significantly improved forecast results and greatly reduces conditional variances.
Kepler AutoRegressive Planet Search
Caceres, Gabriel Antonio; Feigelson, Eric
2016-01-01
The Kepler AutoRegressive Planet Search (KARPS) project uses statistical methodology associated with autoregressive (AR) processes to model Kepler lightcurves in order to improve exoplanet transit detection in systems with high stellar variability. We also introduce a planet-search algorithm to detect transits in time-series residuals after application of the AR models. One of the main obstacles in detecting faint planetary transits is the intrinsic stellar variability of the host star. The variability displayed by many stars may have autoregressive properties, wherein later flux values are correlated with previous ones in some manner. Our analysis procedure consisting of three steps: pre-processing of the data to remove discontinuities, gaps and outliers; AR-type model selection and fitting; and transit signal search of the residuals using a new Transit Comb Filter (TCF) that replaces traditional box-finding algorithms. The analysis procedures of the project are applied to a portion of the publicly available Kepler light curve data for the full 4-year mission duration. Tests of the methods have been made on a subset of Kepler Objects of Interest (KOI) systems, classified both as planetary `candidates' and `false positives' by the Kepler Team, as well as a random sample of unclassified systems. We find that the ARMA-type modeling successfully reduces the stellar variability, by a factor of 10 or more in active stars and by smaller factors in more quiescent stars. A typical quiescent Kepler star has an interquartile range (IQR) of ~10 e-/sec, which may improve slightly after modeling, while those with IQR ranging from 20 to 50 e-/sec, have improvements from 20% up to 70%. High activity stars (IQR exceeding 100) markedly improve. A periodogram based on the TCF is constructed to concentrate the signal of these periodic spikes. When a periodic transit is found, the model is displayed on a standard period-folded averaged light curve. Our findings to date on real
Dodani, Sheel C.; Kiss, Gert; Cahn, Jackson K. B.; Su, Ye; Pande, Vijay S.; Arnold, Frances H.
2016-05-01
The dynamic motions of protein structural elements, particularly flexible loops, are intimately linked with diverse aspects of enzyme catalysis. Engineering of these loop regions can alter protein stability, substrate binding and even dramatically impact enzyme function. When these flexible regions are unresolvable structurally, computational reconstruction in combination with large-scale molecular dynamics simulations can be used to guide the engineering strategy. Here we present a collaborative approach that consists of both experiment and computation and led to the discovery of a single mutation in the F/G loop of the nitrating cytochrome P450 TxtE that simultaneously controls loop dynamics and completely shifts the enzyme's regioselectivity from the C4 to the C5 position of L-tryptophan. Furthermore, we find that this loop mutation is naturally present in a subset of homologous nitrating P450s and confirm that these uncharacterized enzymes exclusively produce 5-nitro-L-tryptophan, a previously unknown biosynthetic intermediate.
Dodani, Sheel C; Kiss, Gert; Cahn, Jackson K B; Su, Ye; Pande, Vijay S; Arnold, Frances H
2016-05-01
The dynamic motions of protein structural elements, particularly flexible loops, are intimately linked with diverse aspects of enzyme catalysis. Engineering of these loop regions can alter protein stability, substrate binding and even dramatically impact enzyme function. When these flexible regions are unresolvable structurally, computational reconstruction in combination with large-scale molecular dynamics simulations can be used to guide the engineering strategy. Here we present a collaborative approach that consists of both experiment and computation and led to the discovery of a single mutation in the F/G loop of the nitrating cytochrome P450 TxtE that simultaneously controls loop dynamics and completely shifts the enzyme's regioselectivity from the C4 to the C5 position of L-tryptophan. Furthermore, we find that this loop mutation is naturally present in a subset of homologous nitrating P450s and confirm that these uncharacterized enzymes exclusively produce 5-nitro-L-tryptophan, a previously unknown biosynthetic intermediate. PMID:27102675
Massey, J. L.
1975-01-01
A regular Markov source is defined as the output of a deterministic, but noisy, channel driven by the state sequence of a regular finite-state Markov chain. The rate of such a source is the per letter uncertainty of its digits. The well-known result that the rate of a unifilar regular Markov source is easily calculable is demonstrated, where unifilarity means that the present state of the Markov chain and the next output of the deterministic channel uniquely determine the next state. At present, there is no known method to calculate the rate of a nonunifilar source. Two tentative approaches to this unsolved problem are given, namely source identical twins and the master-slave source, which appear to shed some light on the question of rate calculation for a nonunifilar source.
Bidirectional Texture Function Simultaneous Autoregressive Model
Haindl, Michal; Havlíček, Michal
Berlin: Springer, 2012, s. 149-159. (Lecture Notes in Computer Science. 7252). ISBN 978-3-642-32435-2. ISSN 0302-9743. [MUSCLE. Pisa (IT), 13.12.2011-15.12.2011] R&D Projects: GA MŠk 1M0572; GA ČR GA102/08/0593; GA ČR GAP103/11/0335 Grant ostatní: CESNET(CZ) 387/2010 Institutional support: RVO:67985556 Keywords : bidirectional texture function * texture analysis * texture synthesis * data compression * virtual reality Subject RIV: BD - Theory of Information http://library.utia.cas.cz/separaty/2012/RO/haindl-bidirectional texture function simultaneous autoregressive model.pdf
Model reduction methods for vector autoregressive processes
Brüggemann, Ralf
2004-01-01
1. 1 Objective of the Study Vector autoregressive (VAR) models have become one of the dominant research tools in the analysis of macroeconomic time series during the last two decades. The great success of this modeling class started with Sims' (1980) critique of the traditional simultaneous equation models (SEM). Sims criticized the use of 'too many incredible restrictions' based on 'supposed a priori knowledge' in large scale macroeconometric models which were popular at that time. Therefore, he advo cated largely unrestricted reduced form multivariate time series models, unrestricted VAR models in particular. Ever since his influential paper these models have been employed extensively to characterize the underlying dynamics in systems of time series. In particular, tools to summarize the dynamic interaction between the system variables, such as impulse response analysis or forecast error variance decompo sitions, have been developed over the years. The econometrics of VAR models and related quantities i...
Autoregressive Time Series Forecasting of Computational Demand
Sandholm, Thomas
2007-01-01
We study the predictive power of autoregressive moving average models when forecasting demand in two shared computational networks, PlanetLab and Tycoon. Demand in these networks is very volatile, and predictive techniques to plan usage in advance can improve the performance obtained drastically. Our key finding is that a random walk predictor performs best for one-step-ahead forecasts, whereas ARIMA(1,1,0) and adaptive exponential smoothing models perform better for two and three-step-ahead forecasts. A Monte Carlo bootstrap test is proposed to evaluate the continuous prediction performance of different models with arbitrary confidence and statistical significance levels. Although the prediction results differ between the Tycoon and PlanetLab networks, we observe very similar overall statistical properties, such as volatility dynamics.
Bielecki, Tomasz R.; Jakubowski, Jacek; Niewęgłowski, Mariusz
2011-01-01
This article continues our study of Markovian consistency and Markov copulae. In particular, we characterize the weak Markovian consistency for finite Markov chains. We discuss some aspects of dependence between the components of a multivariate Markov chain in the context of weak Markovian consistency and strong Markovian consistency. In this connection, we also introduce and discuss the concept of weak Markov copulae.
R.J. Boys
2002-01-01
Full Text Available This paper describes a Bayesian approach to determining the order of a finite state Markov chain whose transition probabilities are themselves governed by a homogeneous finite state Markov chain. It extends previous work on homogeneous Markov chains to more general and applicable hidden Markov models. The method we describe uses a Markov chain Monte Carlo algorithm to obtain samples from the (posterior distribution for both the order of Markov dependence in the observed sequence and the other governing model parameters. These samples allow coherent inferences to be made straightforwardly in contrast to those which use information criteria. The methods are illustrated by their application to both simulated and real data sets.
Microstructure Image Simulation of Minced Pork Based on Markov Random Field%基于Markov随机场的猪肉糜微结构图像模拟
李华北; 赵杰文
2001-01-01
A stochastic simulation model of minced pork microstructure image was derived with the help of Markov random field theory and Gibbs distribution. The minced pork images of various microstructure were simulated iteratively, and the obtained images were compared with their original ones. The analysis and simulation for the microstructure images of minced food material are key processes in quantitatively studying the influence of microstructure pattern on rheological behavior. By getting the geometry features of minced food material microstructure from the known rheological behavior, the dynamic mechanism and process of the microstructure can be investigated and studied further, therefore the relationship between the rheological behavior and the microstructure was founded. So the conditions quantitatively describing rheological behavior of the minced food material were provided.%利用Markov随机场和Gibbs分布理论，建立了猪肉糜微结构图像的随机场模型，然后通过迭代方法，对不同微结构的猪肉糜图像进行了随机模拟，同时对随机模拟图像和原始图像作了对比分析。 糜状食品物料微观结构图像的分析和模拟是定量研究其微结构模式形态对流变特性影响的关键问题。通过从已知流变特性反演糜状食品物料微结构的几何形态，可以更深入地探讨、研究微结构形成的动力学机制和过程，进而沟通流变特性和微结构形态之间的联系，从而为定量描述糜状食品物料的流变特性提供了条件。
Continuous Time Markov Networks
El-Hay, Tal; Friedman, Nir; Koller, Daphne; Kupferman, Raz
2012-01-01
A central task in many applications is reasoning about processes that change in a continuous time. The mathematical framework of Continuous Time Markov Processes provides the basic foundations for modeling such systems. Recently, Nodelman et al introduced continuous time Bayesian networks (CTBNs), which allow a compact representation of continuous-time processes over a factored state space. In this paper, we introduce continuous time Markov networks (CTMNs), an alternative representation lang...
Stable continuous-time autoregressive process driven by stable subordinator
Wyłomańska, Agnieszka; Gajda, Janusz
2016-02-01
In this paper we examine the continuous-time autoregressive moving average process driven by α-stable Lévy motion delayed by inverse stable subordinator. This process can be applied to high-frequency data with visible jumps and so-called "trapping-events". Those properties are often visible in financial time series but also in amorphous semiconductors, technical data describing the rotational speed of a machine working under various load regimes or data related to indoor air quality. We concentrate on the main characteristics of the examined subordinated process expressed in the language of the measures of dependence which are main tools used in statistical investigation of real data. However, because the analyzed system is based on the α-stable distribution therefore we cannot consider here the correlation (or covariance) as a main measure which indicates at the dependence inside the process. In the paper we examine the codifference, the more general measure of dependence defined for wide class of processes. Moreover we present the simulation procedure of the considered system and indicate how to estimate its parameters. The theoretical results we illustrate by the simulated data analysis.
Dealing with Multiple Solutions in Structural Vector Autoregressive Models.
Beltz, Adriene M; Molenaar, Peter C M
2016-01-01
Structural vector autoregressive models (VARs) hold great potential for psychological science, particularly for time series data analysis. They capture the magnitude, direction of influence, and temporal (lagged and contemporaneous) nature of relations among variables. Unified structural equation modeling (uSEM) is an optimal structural VAR instantiation, according to large-scale simulation studies, and it is implemented within an SEM framework. However, little is known about the uniqueness of uSEM results. Thus, the goal of this study was to investigate whether multiple solutions result from uSEM analysis and, if so, to demonstrate ways to select an optimal solution. This was accomplished with two simulated data sets, an empirical data set concerning children's dyadic play, and modifications to the group iterative multiple model estimation (GIMME) program, which implements uSEMs with group- and individual-level relations in a data-driven manner. Results revealed multiple solutions when there were large contemporaneous relations among variables. Results also verified several ways to select the correct solution when the complete solution set was generated, such as the use of cross-validation, maximum standardized residuals, and information criteria. This work has immediate and direct implications for the analysis of time series data and for the inferences drawn from those data concerning human behavior. PMID:27093380
Autoregressive logistic regression applied to atmospheric circulation patterns
Guanche, Y.; Mínguez, R.; Méndez, F. J.
2014-01-01
Autoregressive logistic regression models have been successfully applied in medical and pharmacology research fields, and in simple models to analyze weather types. The main purpose of this paper is to introduce a general framework to study atmospheric circulation patterns capable of dealing simultaneously with: seasonality, interannual variability, long-term trends, and autocorrelation of different orders. To show its effectiveness on modeling performance, daily atmospheric circulation patterns identified from observed sea level pressure fields over the Northeastern Atlantic, have been analyzed using this framework. Model predictions are compared with probabilities from the historical database, showing very good fitting diagnostics. In addition, the fitted model is used to simulate the evolution over time of atmospheric circulation patterns using Monte Carlo method. Simulation results are statistically consistent with respect to the historical sequence in terms of (1) probability of occurrence of the different weather types, (2) transition probabilities and (3) persistence. The proposed model constitutes an easy-to-use and powerful tool for a better understanding of the climate system.
El Yazid Boudaren, Mohamed; Monfrini, Emmanuel; Pieczynski, Wojciech; Aïssani, Amar
2014-11-01
Hidden Markov chains have been shown to be inadequate for data modeling under some complex conditions. In this work, we address the problem of statistical modeling of phenomena involving two heterogeneous system states. Such phenomena may arise in biology or communications, among other fields. Namely, we consider that a sequence of meaningful words is to be searched within a whole observation that also contains arbitrary one-by-one symbols. Moreover, a word may be interrupted at some site to be carried on later. Applying plain hidden Markov chains to such data, while ignoring their specificity, yields unsatisfactory results. The Phasic triplet Markov chain, proposed in this paper, overcomes this difficulty by means of an auxiliary underlying process in accordance with the triplet Markov chains theory. Related Bayesian restoration techniques and parameters estimation procedures according to the new model are then described. Finally, to assess the performance of the proposed model against the conventional hidden Markov chain model, experiments are conducted on synthetic and real data. PMID:26353069
Zhao Haijun; Ma Yan; Huang Xiaohong; Su Yujie
2008-01-01
Predicting heartbeat message arrival time is crucial for the quality of failure detection service over internet. However, internet dynamic characteristics make it very difficult to understand message behavior and accurately predict heartbeat arrival time. To solve this problem, a novel black-box model is proposed to predict the next heartbeat arrival time. Heartbeat arrival time is modeled as auto-regressive process, heartbeat sending time is modeled as exogenous variable, the model's coefficients are estimated based on the sliding window of observations and this result is used to predict the next heartbeat arrival time. Simulation shows that this adaptive auto-regressive exogenous (ARX) model can accurately capture heartbeat arrival dynamics and minimize prediction error in different network environments.
In the past few decades many types of structural damage indices based on structural health monitoring signals have been proposed, requiring performance evaluation and comparison studies on these indices in a quantitative manner. One tool to help accomplish this objective is analytical sensitivity analysis, which has been successfully used to evaluate the influences of system operational parameters on observable characteristics in many fields of study. In this paper, the sensitivity expressions of two damage features, namely the Mahalanobis distance of autoregressive coefficients and the Cosh distance of autoregressive spectra, will be derived with respect to both structural damage and measurement noise level. The effectiveness of the proposed methods is illustrated in a numerical case study on a 10-DOF system, where their results are compared with those from direct simulation and theoretical calculation. (paper)
Putting Markov Chains Back into Markov Chain Monte Carlo
Barker, Richard J.; Schofield, Matthew R.
2007-01-01
Markov chain theory plays an important role in statistical inference both in the formulation of models for data and in the construction of efficient algorithms for inference. The use of Markov chains in modeling data has a long history, however the use of Markov chain theory in developing algorithms for statistical inference has only become popular recently. Using mark-recapture models as an illustration, we show how Markov chains can be used for developing demographic models and also ...
Hidden hybrid Markov/semi-Markov chains.
GUÉDON, YANN
2005-01-01
http://www.sciencedirect.com/science?ₒb=IssueURL&_tockey=%23TOC%235880%232005%23999509996%23596026%23FLA%23&ₐuth=y&view=c&ₐcct=C000056834&_version=1&_urlVersion=0&_userid=2292769&md5=87e7f8be94f92a8574da566c600ce631 International audience Models that combine Markovian states with implicit geometric state occupancy distributions and semi-Markovian states with explicit state occupancy distributions, are investigated. This type of model retains the flexibility of hidden semi-Markov chains ...
Markov chains for testing redundant software
White, Allan L.; Sjogren, Jon A.
1988-01-01
A preliminary design for a validation experiment has been developed that addresses several problems unique to assuring the extremely high quality of multiple-version programs in process-control software. The procedure uses Markov chains to model the error states of the multiple version programs. The programs are observed during simulated process-control testing, and estimates are obtained for the transition probabilities between the states of the Markov chain. The experimental Markov chain model is then expanded into a reliability model that takes into account the inertia of the system being controlled. The reliability of the multiple version software is computed from this reliability model at a given confidence level using confidence intervals obtained for the transition probabilities during the experiment. An example demonstrating the method is provided.
Estimation of Time Varying Autoregressive Symmetric Alpha Stable
National Aeronautics and Space Administration — In this work, we present a novel method for modeling time-varying autoregressive impulsive signals driven by symmetric alpha stable distributions. The proposed...
Modeling non-Gaussian time-varying vector autoregressive process
National Aeronautics and Space Administration — We present a novel and general methodology for modeling time-varying vector autoregressive processes which are widely used in many areas such as modeling of...
Cardiac arrhythmia classification using autoregressive modeling
Srinivasan Narayanan
2002-11-01
Full Text Available Abstract Background Computer-assisted arrhythmia recognition is critical for the management of cardiac disorders. Various techniques have been utilized to classify arrhythmias. Generally, these techniques classify two or three arrhythmias or have significantly large processing times. A simpler autoregressive modeling (AR technique is proposed to classify normal sinus rhythm (NSR and various cardiac arrhythmias including atrial premature contraction (APC, premature ventricular contraction (PVC, superventricular tachycardia (SVT, ventricular tachycardia (VT and ventricular fibrillation (VF. Methods AR Modeling was performed on ECG data from normal sinus rhythm as well as various arrhythmias. The AR coefficients were computed using Burg's algorithm. The AR coefficients were classified using a generalized linear model (GLM based algorithm in various stages. Results AR modeling results showed that an order of four was sufficient for modeling the ECG signals. The accuracy of detecting NSR, APC, PVC, SVT, VT and VF were 93.2% to 100% using the GLM based classification algorithm. Conclusion The results show that AR modeling is useful for the classification of cardiac arrhythmias, with reasonably high accuracies. Further validation of the proposed technique will yield acceptable results for clinical implementation.
Turner, Sean; Galelli, Stefano; Wilcox, Karen
2015-04-01
Water reservoir systems are often affected by recurring large-scale ocean-atmospheric anomalies, known as teleconnections, that cause prolonged periods of climatological drought. Accurate forecasts of these events -- at lead times in the order of weeks and months -- may enable reservoir operators to take more effective release decisions to improve the performance of their systems. In practice this might mean a more reliable water supply system, a more profitable hydropower plant or a more sustainable environmental release policy. To this end, climate indices, which represent the oscillation of the ocean-atmospheric system, might be gainfully employed within reservoir operating models that adapt the reservoir operation as a function of the climate condition. This study develops a Stochastic Dynamic Programming (SDP) approach that can incorporate climate indices using a Hidden Markov Model. The model simulates the climatic regime as a hidden state following a Markov chain, with the state transitions driven by variation in climatic indices, such as the Southern Oscillation Index. Time series analysis of recorded streamflow data reveals the parameters of separate autoregressive models that describe the inflow to the reservoir under three representative climate states ("normal", "wet", "dry"). These models then define inflow transition probabilities for use in a classic SDP approach. The key advantage of the Hidden Markov Model is that it allows conditioning the operating policy not only on the reservoir storage and the antecedent inflow, but also on the climate condition, thus potentially allowing adaptability to a broader range of climate conditions. In practice, the reservoir operator would effect a water release tailored to a specific climate state based on available teleconnection data and forecasts. The approach is demonstrated on the operation of a realistic, stylised water reservoir with carry-over capacity in South-East Australia. Here teleconnections relating
Monitoring time-varying parameters in an autoregression
Carsoule, Frédéric; Franses, Philip Hans
1999-01-01
textabstractWe develop a sequential testing approach for a structural change in the parameters of an autoregression, which amounts to a monitoring procedure with a controlled asymptotic size as we repeat the test. Our method can be used as a general misspecification test. We apply our method to monthly US industrial production in order to investigate if its autoregressive behavior and/or its innovation variance have changed during the twentieth century.
Inference of High-dimensional Autoregressive Generalized Linear Models
Hall, Eric C.; Raskutti, Garvesh; Willett, Rebecca
2016-01-01
Vector autoregressive models characterize a variety of time series in which linear combinations of current and past observations can be used to accurately predict future observations. For instance, each element of an observation vector could correspond to a different node in a network, and the parameters of an autoregressive model would correspond to the impact of the network structure on the time series evolution. Often these models are used successfully in practice to learn the structure of...
On the range of validity of the autoregressive sieve bootstrap
Kreiss, Jens-Peter; Paparoditis, Efstathios; Politis, Dimitris N.
2012-01-01
We explore the limits of the autoregressive (AR) sieve bootstrap, and show that its applicability extends well beyond the realm of linear time series as has been previously thought. In particular, for appropriate statistics, the AR-sieve bootstrap is valid for stationary processes possessing a general Wold-type autoregressive representation with respect to a white noise; in essence, this includes all stationary, purely nondeterministic processes, whose spectral density is everywhere positive....
Sensitivity of hidden Markov models
Mitrophanov, Alexander Yu.; Lomsadze, Alexandre; Borodovsky, Mark
2005-01-01
We derive a tight perturbation bound for hidden Markov models. Using this bound, we show that, in many cases, the distribution of a hidden Markov model is considerably more sensitive to perturbations in the emission probabilities than to perturbations in the transition probability matrix and the initial distribution of the underlying Markov chain. Our approach can also be used to assess the sensitivity of other stochastic models, such as mixture processes and semi-Markov ...
A new Markov Binomial distribution.
Omey, Edward; Minkova, Leda D.
2011-01-01
In this paper, we introduce a two state homogeneous Markov chain and define a geometric distribution related to this Markov chain. We define also the negative binomial distribution similar to the classical case and call it NB related to interrupted Markov chain. The new binomial distribution is related to the interrupted Markov chain. Some characterization properties of the Geometric distributions are given. Recursion formulas and probability mass functions for the NB distribution and the new...
On Markov Chains and Filtrations
Spreij, Peter
1997-01-01
In this paper we rederive some well known results for continuous time Markov processes that live on a finite state space.Martingale techniques are used throughout the paper. Special attention is paid to the construction of a continuous timeMarkov process, when we start from a discrete time Markov chain. The Markov property here holds with respect tofiltrations that need not be minimal.
CONVERGENCE OF MARKOV CHAIN APPROXIMATIONS TO STOCHASTIC REACTION DIFFUSION EQUATIONS
Kouritzin, Michael A.; Hongwei Long
2001-01-01
In the context of simulating the transport of a chemical or bacterial contaminant through a moving sheet of water, we extend a well-established method of approximating reaction-diffusion equations with Markov chains by allowing convection, certain Poisson measure driving sources and a larger class of reaction functions. Our alterations also feature dramatically slower Markov chain state change rates often yielding a ten to one-hundred-fold simulation speed increase over the previous version o...
The Kernel Adaptive Autoregressive-Moving-Average Algorithm.
Li, Kan; Príncipe, José C
2016-02-01
In this paper, we present a novel kernel adaptive recurrent filtering algorithm based on the autoregressive-moving-average (ARMA) model, which is trained with recurrent stochastic gradient descent in the reproducing kernel Hilbert spaces. This kernelized recurrent system, the kernel adaptive ARMA (KAARMA) algorithm, brings together the theories of adaptive signal processing and recurrent neural networks (RNNs), extending the current theory of kernel adaptive filtering (KAF) using the representer theorem to include feedback. Compared with classical feedforward KAF methods, the KAARMA algorithm provides general nonlinear solutions for complex dynamical systems in a state-space representation, with a deferred teacher signal, by propagating forward the hidden states. We demonstrate its capabilities to provide exact solutions with compact structures by solving a set of benchmark nondeterministic polynomial-complete problems involving grammatical inference. Simulation results show that the KAARMA algorithm outperforms equivalent input-space recurrent architectures using first- and second-order RNNs, demonstrating its potential as an effective learning solution for the identification and synthesis of deterministic finite automata. PMID:25935049
The comparison study among several data transformations in autoregressive modeling
Setiyowati, Susi; Waluyo, Ramdhani Try
2015-12-01
In finance, the adjusted close of stocks are used to observe the performance of a company. The extreme prices, which may increase or decrease drastically, are often become particular concerned since it can impact to bankruptcy. As preventing action, the investors have to observe the future (forecasting) stock prices comprehensively. For that purpose, time series analysis could be one of statistical methods that can be implemented, for both stationary and non-stationary processes. Since the variability process of stocks prices tend to large and also most of time the extreme values are always exist, then it is necessary to do data transformation so that the time series models, i.e. autoregressive model, could be applied appropriately. One of popular data transformation in finance is return model, in addition to ratio of logarithm and some others Tukey ladder transformation. In this paper these transformations are applied to AR stationary models and non-stationary ARCH and GARCH models through some simulations with varying parameters. As results, this work present the suggestion table that shows transformations behavior for some condition of parameters and models. It is confirmed that the better transformation is obtained, depends on type of data distributions. In other hands, the parameter conditions term give significant influence either.
Benchmarking of a Markov multizone model of contaminant transport.
Jones, Rachael M; Nicas, Mark
2014-10-01
A Markov chain model previously applied to the simulation of advection and diffusion process of gaseous contaminants is extended to three-dimensional transport of particulates in indoor environments. The model framework and assumptions are described. The performance of the Markov model is benchmarked against simple conventional models of contaminant transport. The Markov model is able to replicate elutriation predictions of particle deposition with distance from a point source, and the stirred settling of respirable particles. Comparisons with turbulent eddy diffusion models indicate that the Markov model exhibits numerical diffusion in the first seconds after release, but over time accurately predicts mean lateral dispersion. The Markov model exhibits some instability with grid length aspect when turbulence is incorporated by way of the turbulent diffusion coefficient, and advection is present. However, the magnitude of prediction error may be tolerable for some applications and can be avoided by incorporating turbulence by way of fluctuating velocity (e.g. turbulence intensity). PMID:25143517
Partially Hidden Markov Models
Forchhammer, Søren Otto; Rissanen, Jorma
1996-01-01
Partially Hidden Markov Models (PHMM) are introduced. They differ from the ordinary HMM's in that both the transition probabilities of the hidden states and the output probabilities are conditioned on past observations. As an illustration they are applied to black and white image compression where...
Partially Hidden Markov Models
Forchhammer, Søren Otto; Rissanen, Jorma
1996-01-01
Partially Hidden Markov Models (PHMM) are introduced. They differ from the ordinary HMM's in that both the transition probabilities of the hidden states and the output probabilities are conditioned on past observations. As an illustration they are applied to black and white image compression wher...
Kohlenbach, Ulrich Wilhelm
We show that the so-called weak Markov's principle (WMP) which states that every pseudo-positive real number is positive is underivable in E-HA + AC. Since allows one to formalize (atl eastl arge parts of) Bishop's constructive mathematics, this makes it unlikely that WMP can be proved within the...
Lopes, Sílvia R. C.; Prass, Taiane S.
2014-05-01
Here we present a theoretical study on the main properties of Fractionally Integrated Exponential Generalized Autoregressive Conditional Heteroskedastic (FIEGARCH) processes. We analyze the conditions for the existence, the invertibility, the stationarity and the ergodicity of these processes. We prove that, if { is a FIEGARCH(p,d,q) process then, under mild conditions, { is an ARFIMA(q,d,0) with correlated innovations, that is, an autoregressive fractionally integrated moving average process. The convergence order for the polynomial coefficients that describes the volatility is presented and results related to the spectral representation and to the covariance structure of both processes { and { are discussed. Expressions for the kurtosis and the asymmetry measures for any stationary FIEGARCH(p,d,q) process are also derived. The h-step ahead forecast for the processes {, { and { are given with their respective mean square error of forecast. The work also presents a Monte Carlo simulation study showing how to generate, estimate and forecast based on six different FIEGARCH models. The forecasting performance of six models belonging to the class of autoregressive conditional heteroskedastic models (namely, ARCH-type models) and radial basis models is compared through an empirical application to Brazilian stock market exchange index.
Robust filtering and prediction for systems with embedded finite-state Markov-Chain dynamics
This research developed new methodologies for the design of robust near-optimal filters/predictors for a class of system models that exhibit embedded finite-state Markov-chain dynamics. These methodologies are developed through the concepts and methods of stochastic model building (including time-series analysis), game theory, decision theory, and filtering/prediction for linear dynamic systems. The methodology is based on the relationship between the robustness of a class of time-series models and quantization which is applied to the time series as part of the model identification process. This relationship is exploited by utilizing the concept of an equivalence, through invariance of spectra, between the class of Markov-chain models and the class of autoregressive moving average (ARMA) models. This spectral equivalence permits a straightforward implementation of the desirable robust properties of the Markov-chain approximation in a class of models which may be applied in linear-recursive form in a linear Kalman filter/predictor structure. The linear filter/predictor structure is shown to provide asymptotically optimal estimates of states which represent one or more integrations of the Markov-chain state. The development of a new saddle-point theorem for a game based on the Markov-chain model structure gives rise to a technique for determining a worst case Markov-chain process, upon which a robust filter/predictor design if based
Smith, R. M.
1991-01-01
Numerous applications in the area of computer system analysis can be effectively studied with Markov reward models. These models describe the behavior of the system with a continuous-time Markov chain, where a reward rate is associated with each state. In a reliability/availability model, upstates may have reward rate 1 and down states may have reward rate zero associated with them. In a queueing model, the number of jobs of certain type in a given state may be the reward rate attached to that state. In a combined model of performance and reliability, the reward rate of a state may be the computational capacity, or a related performance measure. Expected steady-state reward rate and expected instantaneous reward rate are clearly useful measures of the Markov reward model. More generally, the distribution of accumulated reward or time-averaged reward over a finite time interval may be determined from the solution of the Markov reward model. This information is of great practical significance in situations where the workload can be well characterized (deterministically, or by continuous functions e.g., distributions). The design process in the development of a computer system is an expensive and long term endeavor. For aerospace applications the reliability of the computer system is essential, as is the ability to complete critical workloads in a well defined real time interval. Consequently, effective modeling of such systems must take into account both performance and reliability. This fact motivates our use of Markov reward models to aid in the development and evaluation of fault tolerant computer systems.
Cohomological dimension of Markov compacta
Dranishnikov, Alexander
2006-01-01
We rephrase Gromov's definition of Markov compacta, introduce a subclass of Markov compacta defined by one building block and study cohomological dimensions of these compacta. We show that for a Markov compactum $X$, $\\dim_{\\Z_{(p)}}X=\\dim_{\\Q}X$ for all but finitely many primes $p$ where $\\Z_{(p)}$ is the localization of $\\Z$ at $p$. We construct Markov compacta of arbitrarily large dimension having $\\dim_{\\Q}X=1$ as well as Markov compacta of arbitrary large rational dimension with $\\dim_{\\...
Mixture latent autoregressive models for longitudinal data
Bartolucci, Francesco; Pennoni, Fulvia
2011-01-01
Many relevant statistical and econometric models for the analysis of longitudinal data include a latent process to account for the unobserved heterogeneity between subjects in a dynamic fashion. Such a process may be continuous (typically an AR(1)) or discrete (typically a Markov chain). In this paper, we propose a model for longitudinal data which is based on a mixture of AR(1) processes with different means and correlation coefficients, but with equal variances. This model belongs to the class of models based on a continuous latent process, and then it has a natural interpretation in many contexts of application, but it is more flexible than other models in this class, reaching a goodness-of-fit similar to that of a discrete latent process model, with a reduced number of parameters. We show how to perform maximum likelihood estimation of the proposed model by the joint use of an Expectation-Maximisation algorithm and a Newton-Raphson algorithm, implemented by means of recursions developed in the hidden Mark...
Variance bounding Markov chains
Roberts, Gareth O.; Jeffrey S. Rosenthal
2008-01-01
We introduce a new property of Markov chains, called variance bounding. We prove that, for reversible chains at least, variance bounding is weaker than, but closely related to, geometric ergodicity. Furthermore, variance bounding is equivalent to the existence of usual central limit theorems for all L2 functionals. Also, variance bounding (unlike geometric ergodicity) is preserved under the Peskun order. We close with some applications to Metropolis–Hastings algorithms.
Nicoulaud-Gouin, V.; Giacalone, M.; Gonze, M.A. [Institut de Radioprotection et de Surete Nucleaire-PRP-ENV/SERIS/LM2E (France); Martin-Garin, A.; Garcia-Sanchez, L. [IRSN-PRP-ENV/SERIS/L2BT (France)
2014-07-01
, distinguishes instantaneous (K{sub d}1) and first-order kinetics of sorption and desorption processes (λ{sub fix}, λ{sub rem}), each having potentially a limited sorption capacity. A Soil-Plant Deposition Model describing the weeds contamination in {sup 137}Cs, {sup 134}Cs and {sup 131}I, with in situ measures in the Fukushima prefecture (Gonze et al. submitted to this conference). This model considers two foliage pools and a root pool, and describes foliar biomass growth with a Verhulst model. One prerequisite for calibration is model identifiability. Here, we showed that there are not unique parameter values corresponding to a data set. However, sharp distributions were found when several data sets were involved. One numerical difficulty of Markov Chains is to check convergence. It was here examined with Raftery and Lewis diagnostic, Gelman and Rubin plots, and simulation trails. Failing to converge may indicate that the model is not adapted to the observations. The Bayes factor was used to decide between competing models, which applies even if they are not nested. For most data series, EK model was preferable to the nested K{sub d} approach. An Empirical Dynamical Model -consisting of two exponential functions- was compared to the Soil-Plant Deposition Model, by distinguishing site-specific parameters and invariant parameters between stations, in order to study the goodness-of-fit of the Soil-Plant Deposition Model. (authors)
instantaneous (Kd1) and first-order kinetics of sorption and desorption processes (λfix, λrem), each having potentially a limited sorption capacity. A Soil-Plant Deposition Model describing the weeds contamination in 137Cs, 134Cs and 131I, with in situ measures in the Fukushima prefecture (Gonze et al. submitted to this conference). This model considers two foliage pools and a root pool, and describes foliar biomass growth with a Verhulst model. One prerequisite for calibration is model identifiability. Here, we showed that there are not unique parameter values corresponding to a data set. However, sharp distributions were found when several data sets were involved. One numerical difficulty of Markov Chains is to check convergence. It was here examined with Raftery and Lewis diagnostic, Gelman and Rubin plots, and simulation trails. Failing to converge may indicate that the model is not adapted to the observations. The Bayes factor was used to decide between competing models, which applies even if they are not nested. For most data series, EK model was preferable to the nested Kd approach. An Empirical Dynamical Model -consisting of two exponential functions- was compared to the Soil-Plant Deposition Model, by distinguishing site-specific parameters and invariant parameters between stations, in order to study the goodness-of-fit of the Soil-Plant Deposition Model. (authors)
Markov or not Markov - this should be a question
Bickenbach, Frank; Bode, Eckhardt
2002-01-01
Although it is well known that Markov process theory, frequently applied in the literature on income convergence, imposes some very restrictive assumptions upon the data generating process, these assumptions have generally been taken for granted so far. The present paper proposes, resp. recalls chi-square tests of the Markov property, of spatial independence, and of homogeneity across time and space to assess the reliability of estimated Markov transition matrices. As an illustration we show ...
A complex autoregressive model and application to monthly temperature forecasts
X. Gu
2005-11-01
Full Text Available A complex autoregressive model was established based on the mathematic derivation of the least squares for the complex number domain which is referred to as the complex least squares. The model is different from the conventional way that the real number and the imaginary number are separately calculated. An application of this new model shows a better forecast than forecasts from other conventional statistical models, in predicting monthly temperature anomalies in July at 160 meteorological stations in mainland China. The conventional statistical models include an autoregressive model, where the real number and the imaginary number are separately disposed, an autoregressive model in the real number domain, and a persistence-forecast model.
Modeling Autoregressive Processes with Moving-Quantiles-Implied Nonlinearity
Isao Ishida
2015-01-01
Full Text Available We introduce and investigate some properties of a class of nonlinear time series models based on the moving sample quantiles in the autoregressive data generating process. We derive a test fit to detect this type of nonlinearity. Using the daily realized volatility data of Standard & Poor’s 500 (S&P 500 and several other indices, we obtained good performance using these models in an out-of-sample forecasting exercise compared with the forecasts obtained based on the usual linear heterogeneous autoregressive and other models of realized volatility.
A Mixture Innovation Heterogeneous Autoregressive Model for Structural Breaks and Long Memory
Nonejad, Nima
We propose a flexible model to describe nonlinearities and long-range dependence in time series dynamics. Our model is an extension of the heterogeneous autoregressive model. Structural breaks occur through mixture distributions in state innovations of linear Gaussian state space models. Monte...... Carlo simulations evaluate the properties of the estimation procedures. Results show that the proposed model is viable and flexible for purposes of forecasting volatility. Model uncertainty is accounted for by employing Bayesian model averaging. Bayesian model averaging provides very competitive...... forecasts compared to any single model specification. It provides further improvements when we average over nonlinear specifications....
A Score Type Test for General Autoregressive Models in Time Series
Jian-hong Wu; Li-xing Zhu
2007-01-01
This paper is devoted to the goodness-of-fit test for the general autoregressive models in time series. By averaging for the weighted residuals, we construct a score type test which is asymptotically standard chi-squared under the null and has some desirable power properties under the alternatives. Specifically, the test is sensitive to alternatives and can detect the alternatives approaching, along a direction, the null at a rate that is arbitrarily close to n-1/2. Furthermore, when the alternatives are not directional, we construct asymptotically distribution-free maximin tests for a large class of alternatives. The performance of the tests is evaluated through simulation studies.
Distribusi Markov-Binomial Negatif
Widyasari, Rina
2015-01-01
The way to find a new distribution of random variables is defining the distribution which associated with Markov chain. In this research, researcher defines all the random variables identically independent distributed negative binomial distribution and form a Markov chain. Suppose that Xn is a sequence of Bernoulli trials that if 1 occurs means ”success” and 0 occurs means ”failure”. Nb(s) defined as random variables sth success in n trials. Each trial form a Markov chain, in n...
Contribution to ECDIS Reliability using Markov Model
Sumić, Dean; Peraković, Dragan; Jurčević, Marinko
2014-01-01
An Integrated Bridge System (IBS) contains a fully duplicated Electronic Chart Display and Information System (ECDIS). Although duplication should increase system reliability, reliability and availability are not improved. Proper ECDIS maintenance includes updating both: the information system and the provided chart system. This procedure, in practice, tends to decrease reliability and availability. A Markov ECDIS simulation model is given. A new design concept is presented and proposed. The ...
Markov Chains For Testing Redundant Software
White, Allan L.; Sjogren, Jon A.
1990-01-01
Preliminary design developed for validation experiment that addresses problems unique to assuring extremely high quality of multiple-version programs in process-control software. Approach takes into account inertia of controlled system in sense it takes more than one failure of control program to cause controlled system to fail. Verification procedure consists of two steps: experimentation (numerical simulation) and computation, with Markov model for each step.
Bayesian Posterior Distributions Without Markov Chains
Cole, Stephen R.; Chu, Haitao; Greenland, Sander; Hamra, Ghassan; Richardson, David B.
2012-01-01
Bayesian posterior parameter distributions are often simulated using Markov chain Monte Carlo (MCMC) methods. However, MCMC methods are not always necessary and do not help the uninitiated understand Bayesian inference. As a bridge to understanding Bayesian inference, the authors illustrate a transparent rejection sampling method. In example 1, they illustrate rejection sampling using 36 cases and 198 controls from a case-control study (1976–1983) assessing the relation between residential ex...
Xiaoyun MO; Jieming ZHOU; Hui OU; Xiangqun YANG
2013-01-01
Given a new Double-Markov risk model DM =(μ,Q,v,H; Y,Z) and Double-Markov risk process U ={U(t),t ≥ 0}.The ruin or survival problem is addressed.Equations which the survival probability satisfied and the formulas of calculating survival probability are obtained.Recursion formulas of calculating the survival probability and analytic expression of recursion items are obtained.The conclusions are expressed by Q matrix for a Markov chain and transition probabilities for another Markov Chain.
Barczy, Matyas; Pap, Gyula
2010-01-01
In this paper the asymptotic behavior of conditional least squares estimators of the autoregressive parameter for nonprimitive unstable integer-valued autoregressive models of order 2 (INAR(2)) is described.
The cointegrated vector autoregressive model with general deterministic terms
Johansen, Søren; Nielsen, Morten Ørregaard
In the cointegrated vector autoregression (CVAR) literature, deterministic terms have until now been analyzed on a case-by-case, or as-needed basis. We give a comprehensive unified treatment of deterministic terms in the additive model X(t)= Z(t) + Y(t), where Z(t) belongs to a large class...
Weak Convergence of the Residual Empirical Process in Explosive Autoregression
Koul, Hira L.; Levental, Shlomo
1989-01-01
This paper proves the weak convergence of the residual empirical process in an explosive autoregression model to the Brownian bridge. As an application the Kolmogorov-Smirnov goodness-of-fit test for testing that the errors have a specified distribution is shown to be asymptotically distribution-free.
Likelihood inference for a nonstationary fractional autoregressive model
Johansen, Søren; Nielsen, Morten Ørregaard
This paper discusses model based inference in an autoregressive model for fractional processes based on the Gaussian likelihood. The model allows for the process to be fractional of order d or d-b; where d ≥ b > 1/2 are parameters to be estimated. We model the data X1,...,XT given the initial val...
Likelihood inference for a nonstationary fractional autoregressive model
Johansen, Søren; Ørregård Nielsen, Morten
2010-01-01
This paper discusses model-based inference in an autoregressive model for fractional processes which allows the process to be fractional of order d or d-b. Fractional differencing involves infinitely many past values and because we are interested in nonstationary processes we model the data X1,.....
Likelihood Inference for a Nonstationary Fractional Autoregressive Model
Johansen, Søren; Nielsen, Morten Ørregaard
This paper discusses model based inference in an autoregressive model for fractional processes based on the Gaussian likelihood. The model allows for the process to be fractional of order d or d - b; where d = b > 1/2 are parameters to be estimated. We model the data X¿, ..., X¿ given the initial...
Nonlinear autoregressive models with heavy-tailed innovation
JIN Yang; AN Hongzhi
2005-01-01
In this paper, we discuss the relationship between the stationary marginal tail probability and the innovation's tail probability of nonlJnear autoregressive models. We show that under certain conditions that ensure the stationarity and ergodicity, one dimension stationary marginal distribution has the heavy-tailed probability property with the same index as that of the innovation's tail probability.
Limit theorems for bifurcating integer-valued autoregressive processes
Blandin, Vassili
2012-01-01
We study the asymptotic behavior of the weighted least squares estimators of the unknown parameters of bifurcating integer-valued autoregressive processes. Under suitable assumptions on the immigration, we establish the almost sure convergence of our estimators, together with the quadratic strong law and central limit theorems. All our investigation relies on asymptotic results for vector-valued martingales.
New GPS-aided SINU System Modeling using an Autoregressive Model
Chot Hun Lim
2015-09-01
Full Text Available Stochastic error in the Micro-Electro-Mechanical-System (MEMS Strapdown Inertial Navigation Unit (SINU is the primary issue causing sensors to be unable to operate as a standalone device. Conventional implementation of MEMS SINU fuses measurement with a global positioning system (GPS through a Kalman filter in order to achieve long-term accuracy. Such integration is known as a GPS-aided SINU system, and its estimation accuracy relies on how precise the stochastic error prediction is in Kalman filtering operation. In this paper, a comprehensive study on stochastic error modeling and analysis through a Gauss- Markov (GM model and autoregressive (AR model are presented. A wavelet denoising technique is introduced prior to error modeling to remove the MEMS SINU's high frequency noise. Without a wavelet denoising technique, neither the GM model nor AR model can be utilized to represent the stochastic error of SINU. Next, details of the Kalman filter implementation to accommodate the AR model are presented. The modeling outcomes are implemented on an unmanned aerial vehicle (UAV for on-board motion sensing. The experimental results show that AR model implementation, compared to a conventional GM model, significantly reduced the estimated errors while preserving the position, velocity and orientation measurements.
Nonlinear Markov processes: Deterministic case
Frank, T.D. [Center for the Ecological Study of Perception and Action, Department of Psychology, University of Connecticut, 406 Babbidge Road, Storrs, CT 06269 (United States)], E-mail: till.frank@uconn.edu
2008-10-06
Deterministic Markov processes that exhibit nonlinear transition mechanisms for probability densities are studied. In this context, the following issues are addressed: Markov property, conditional probability densities, propagation of probability densities, multistability in terms of multiple stationary distributions, stability analysis of stationary distributions, and basin of attraction of stationary distribution.
Markov Random Field Surface Reconstruction
Paulsen, Rasmus Reinhold; Bærentzen, Jakob Andreas; Larsen, Rasmus
2010-01-01
A method for implicit surface reconstruction is proposed. The novelty in this paper is the adaption of Markov Random Field regularization of a distance field. The Markov Random Field formulation allows us to integrate both knowledge about the type of surface we wish to reconstruct (the prior) and...
Nonlinear Markov processes: Deterministic case
Deterministic Markov processes that exhibit nonlinear transition mechanisms for probability densities are studied. In this context, the following issues are addressed: Markov property, conditional probability densities, propagation of probability densities, multistability in terms of multiple stationary distributions, stability analysis of stationary distributions, and basin of attraction of stationary distribution
An interlacing theorem for reversible Markov chains
Reversible Markov chains are an indispensable tool in the modeling of a vast class of physical, chemical, biological and statistical problems. Examples include the master equation descriptions of relaxing physical systems, stochastic optimization algorithms such as simulated annealing, chemical dynamics of protein folding and Markov chain Monte Carlo statistical estimation. Very often the large size of the state spaces requires the coarse graining or lumping of microstates into fewer mesoscopic states, and a question of utmost importance for the validity of the physical model is how the eigenvalues of the corresponding stochastic matrix change under this operation. In this paper we prove an interlacing theorem which gives explicit bounds on the eigenvalues of the lumped stochastic matrix. (fast track communication)
R. Maity; Prasad, D.
2011-01-01
In this paper, Split Markov Process (SMP) is developed to assess one-step-ahead variation of daily rainfall at a rain gauge station. SMP is an advancement of general Markov Process (MP) and specially developed for probabilistic assessment of change in daily rainfall magnitude. The approach is based on a first-order Markov chain to simulate daily rainfall variation at a point through state/sub-state Transitional Probability Matrix (TPM). Th...
Tornadoes and related damage costs: statistical modeling with a semi-Markov approach
Chiara Corini; Guglielmo D'Amico; Filippo Petroni; Flavio Prattico; Raimondo Manca
2015-01-01
We propose a statistical approach to tornadoes modeling for predicting and simulating occurrences of tornadoes and accumulated cost distributions over a time interval. This is achieved by modeling the tornadoes intensity, measured with the Fujita scale, as a stochastic process. Since the Fujita scale divides tornadoes intensity into six states, it is possible to model the tornadoes intensity by using Markov and semi-Markov models. We demonstrate that the semi-Markov approach is able to reprod...
Markov chains theory and applications
Sericola, Bruno
2013-01-01
Markov chains are a fundamental class of stochastic processes. They are widely used to solve problems in a large number of domains such as operational research, computer science, communication networks and manufacturing systems. The success of Markov chains is mainly due to their simplicity of use, the large number of available theoretical results and the quality of algorithms developed for the numerical evaluation of many metrics of interest.The author presents the theory of both discrete-time and continuous-time homogeneous Markov chains. He carefully examines the explosion phenomenon, the
Quadratic Variation by Markov Chains
Hansen, Peter Reinhard; Horel, Guillaume
We introduce a novel estimator of the quadratic variation that is based on the the- ory of Markov chains. The estimator is motivated by some general results concerning filtering contaminated semimartingales. Specifically, we show that filtering can in prin- ciple remove the effects of market...... microstructure noise in a general framework where little is assumed about the noise. For the practical implementation, we adopt the dis- crete Markov chain model that is well suited for the analysis of financial high-frequency prices. The Markov chain framework facilitates simple expressions and elegant analyti...
Parameter Estimation for Generalized Brownian Motion with Autoregressive Increments
Fendick, Kerry
2011-01-01
This paper develops methods for estimating parameters for a generalization of Brownian motion with autoregressive increments called a Brownian ray with drift. We show that a superposition of Brownian rays with drift depends on three types of parameters - a drift coefficient, autoregressive coefficients, and volatility matrix elements, and we introduce methods for estimating each of these types of parameters using multidimensional times series data. We also cover parameter estimation in the contexts of two applications of Brownian rays in the financial sphere: queuing analysis and option valuation. For queuing analysis, we show how samples of queue lengths can be used to estimate the conditional expectation functions for the length of the queue and for increments in its net input and lost potential output. For option valuation, we show how the Black-Scholes-Merton formula depends on the price of the security on which the option is written through estimates not only of its volatility, but also of a coefficient ...
Bias-corrected estimation in potentially mildly explosive autoregressive models
Haufmann, Hendrik; Kruse, Robinson
This paper provides a comprehensive Monte Carlo comparison of different finite-sample bias-correction methods for autoregressive processes. We consider classic situations where the process is either stationary or exhibits a unit root. Importantly, the case of mildly explosive behaviour is studied...... indirect inference approach oers a valuable alternative to other existing techniques. Its performance (measured by its bias and root mean squared error) is balanced and highly competitive across many different settings. A clear advantage is its applicability for mildly explosive processes. In an empirical...... application to a long annual US Debt/GDP series we consider rolling window estimation of autoregressive models. We find substantial evidence for time-varying persistence and periods of explosiveness during the Civil War and World War II. During the recent years, the series is nearly explosive again. Further...
On the range of validity of the autoregressive sieve bootstrap
Kreiss, Jens-Peter; Politis, Dimitris N; 10.1214/11-AOS900
2012-01-01
We explore the limits of the autoregressive (AR) sieve bootstrap, and show that its applicability extends well beyond the realm of linear time series as has been previously thought. In particular, for appropriate statistics, the AR-sieve bootstrap is valid for stationary processes possessing a general Wold-type autoregressive representation with respect to a white noise; in essence, this includes all stationary, purely nondeterministic processes, whose spectral density is everywhere positive. Our main theorem provides a simple and effective tool in assessing whether the AR-sieve bootstrap is asymptotically valid in any given situation. In effect, the large-sample distribution of the statistic in question must only depend on the first and second order moments of the process; prominent examples include the sample mean and the spectral density. As a counterexample, we show how the AR-sieve bootstrap is not always valid for the sample autocovariance even when the underlying process is linear.
Compressing redundant information in Markov chains
Aletti, Giacomo
2006-01-01
Given a strongly stationary Markov chain and a finite set of stopping rules, we prove the existence of a polynomial algorithm which projects the Markov chain onto a minimal Markov chain without redundant information. Markov complexity is hence defined and tested on some classical problems.
D. G. Partridge
2012-03-01
Full Text Available This paper presents a novel approach to investigate cloud-aerosol interactions by coupling a Markov chain Monte Carlo (MCMC algorithm to an adiabatic cloud parcel model. Despite the number of numerical cloud-aerosol sensitivity studies previously conducted few have used statistical analysis tools to investigate the global sensitivity of a cloud model to input aerosol physiochemical parameters. Using numerically generated cloud droplet number concentration (CDNC distributions (i.e. synthetic data as cloud observations, this inverse modelling framework is shown to successfully estimate the correct calibration parameters, and their underlying posterior probability distribution.
The employed analysis method provides a new, integrative framework to evaluate the global sensitivity of the derived CDNC distribution to the input parameters describing the lognormal properties of the accumulation mode aerosol and the particle chemistry. To a large extent, results from prior studies are confirmed, but the present study also provides some additional insights. There is a transition in relative sensitivity from very clean marine Arctic conditions where the lognormal aerosol parameters representing the accumulation mode aerosol number concentration and mean radius and are found to be most important for determining the CDNC distribution to very polluted continental environments (aerosol concentration in the accumulation mode >1000 cm^{−3} where particle chemistry is more important than both number concentration and size of the accumulation mode.
The competition and compensation between the cloud model input parameters illustrates that if the soluble mass fraction is reduced, the aerosol number concentration, geometric standard deviation and mean radius of the accumulation mode must increase in order to achieve the same CDNC distribution.
This study demonstrates that inverse modelling provides a flexible, transparent and
Decision analysis in clinical radiology by means of Markov modeling
Markov models (Multistate transition models) are mathematical tools to simulate a cohort of individuals followed over time to assess the prognosis resulting from different strategies. They are applied on the assumption that persons are in one of a finite number of states of health (Markov states). Each condition is given a transition probability as well as an incremental value. Probabilities may be chosen constant or varying over time due to predefined rules. Time horizon is divided into equal increments (Markov cycles). The model calculates quality-adjusted life expectancy employing real-life units and values and summing up the length of time spent in each health state adjusted for objective outcomes and subjective appraisal. This sort of modeling prognosis for a given patient is analogous to utility in common decision trees. Markov models can be evaluated by matrix algebra, probabilistic cohort simulation and Monte Carlo simulation. They have been applied to assess the relative benefits and risks of a limited number of diagnostic and therapeutic procedures in radiology. More interventions should be submitted to Markov analyses in order to elucidate their cost-effectiveness. (orig.)
CICAAR - Convolutive ICA with an Auto-Regressive Inverse Model
Dyrholm, Mads; Hansen, Lars Kai
2004-01-01
We invoke an auto-regressive IIR inverse model for convolutive ICA and derive expressions for the likelihood and its gradient. We argue that optimization will give a stable inverse. When there are more sensors than sources the mixing model parameters are estimated in a second step by least square...... estimation. We demonstrate the method on synthetic data and finally separate speech and music in a real room recording....
Structural vector autoregressions: Theory of identification and algorithms for inference
Rubio-Ramírez, Juan F.; Waggoner, Daniel F.; Zha, Tao
2008-01-01
Structural vector autoregressions (SVARs) are widely used for policy analysis and to provide stylized facts for dynamic general equilibrium models. Yet there have been no workable rank conditions to ascertain whether an SVAR is globally identified. When identifying restrictions such as long-run restrictions are imposed on impulse responses, there have been no efficient algorithms for small-sample estimation and inference. To fill these important gaps in the literature, this paper makes four c...
Robust estimation of nonstationary, fractionally integrated, autoregressive, stochastic volatility
Mark J. Jensen
2015-01-01
Empirical volatility studies have discovered nonstationary, long-memory dynamics in the volatility of the stock market and foreign exchange rates. This highly persistent, infinite variance - but still mean reverting - behavior is commonly found with nonparametric estimates of the fractional differencing parameter d, for financial volatility. In this paper, a fully parametric Bayesian estimator, robust to nonstationarity, is designed for the fractionally integrated, autoregressive, stochastic ...
A Simple Cointegrating Rank Test Without Vector Autoregression
Mototsugu Shintani
2000-01-01
This paper proposes a fully nonparametric test for cointegrating rank which does not require estimation of a vector autoregressive model. The test exploits the fact that the degeneracy in the moment matrix of the variables with mixed integration order corresponds to the notion of cointegration. With an appropriate standardization, the test statistics are shown to have a nuisance parameter free limiting distribution and to be consistent under reasonable conditions. Monte Carlo experiments also...
Interest rate pass-through estimates from vector autoregressive models
Burgstaller, Johann
2005-01-01
The empirical literature on interest rate transmission presents diverse and sometimes conflicting estimates. By discussing methodological and specification-related issues, the results of this paper contribute to the understanding of these differences. Eleven Austrian bank lending and deposit rates are utilized to illustrate the pass-through of impulses from monetary policy and banks’ cost of funds. Results from vector autoregressions suggest that the long-run pass-through is higher for moveme...
Adaptive Estimation of Autoregressive Models with Time-Varying Variances
Ke-Li Xu; Phillips, Peter C. B.
2006-01-01
Stable autoregressive models of known finite order are considered with martingale differences errors scaled by an unknown nonparametric time-varying function generating heterogeneity. An important special case involves structural change in the error variance, but in most practical cases the pattern of variance change over time is unknown and may involve shifts at unknown discrete points in time, continuous evolution or combinations of the two. This paper develops kernel-based estimators of th...
Forecasting with time-varying vector autoregressive models
Triantafyllopoulos, K.
2008-01-01
The purpose of this paper is to propose a time-varying vector autoregressive model (TV-VAR) for forecasting multivariate time series. The model is casted into a state-space form that allows flexible description and analysis. The volatility covariance matrix of the time series is modelled via inverted Wishart and singular multivariate beta distributions allowing a fully conjugate Bayesian inference. Model performance and model comparison is done via the likelihood function, sequential Bayes fa...
Testing exact rational expectations in cointegrated vector autoregressive models
Johansen, Søren; Swensen, Anders Rygh
1999-01-01
This paper considers the testing of restrictions implied by rational expectations hypotheses in a cointegrated vector autoregressive model for I(1) variables. If the rational expectations involve one-step-ahead observations only and the coefficients are known, an explicit parameterization of the ...... restrictions is found, and the maximum-likelihood estimator is derived by regression and reduced rank regression. An application is given to a present value model....
Asymptotic results for bifurcating random coefficient autoregressive processes
Blandin, Vassili
2012-01-01
The purpose of this paper is to study the asymptotic behavior of the weighted least square estimators of the unknown parameters of random coefficient bifurcating autoregressive processes. Under suitable assumptions on the immigration and the inheritance, we establish the almost sure convergence of our estimators, as well as a quadratic strong law and central limit theorems. Our study mostly relies on limit theorems for vector-valued martingales.
UV Index Modeling by Autoregressive Distributed Lag (ADL Model)
Alexandre Boleira Lopo; Maria Helena Constantino Spyrides; Paulo Sérgio Lucio; Javier Sigró
2014-01-01
The objective of this work is to model statistically the ultraviolet radiation index (UV Index) to make forecast (extrapolate) and analyze trends. The task is relevant, due to increased UV flux and high rate of cases non-melanoma skin cancer in northeast of Brazil. The methodology utilized an Autoregressive Distributed Lag model (ADL) or Dynamic Linear Regression model. The monthly data of UV index were measured in east coast of the Brazilian Northeast (City of Natal-Rio G...
Stock price forecasting: autoregressive modelling and fuzzy neural network
Marcek, Dusan
2000-01-01
Most models for the time series of stock prices have centered on autoregressive (AR) processes. Traditionaly, fundamantal Box-Jenkins analysis [3] have been the mainstream methodology used to develop time series models. Next, we briefly describe the develop a classical AR model for stock price forecasting. Then a fuzzy regression model is then introduced Following this description, an artificial fuzzy neural network based on B-spline member ship function is presented as an alternative to ...
CICAAR - Convolutive ICA with an Auto-Regressive Inverse Model
Dyrholm, Mads; Hansen, Lars Kai
2004-01-01
We invoke an auto-regressive IIR inverse model for convolutive ICA and derive expressions for the likelihood and its gradient. We argue that optimization will give a stable inverse. When there are more sensors than sources the mixing model parameters are estimated in a second step by least squares estimation. We demonstrate the method on synthetic data and finally separate speech and music in a real room recording.
Dynamic modeling of presence of occupants using inhomogeneous Markov chains
Andersen, Philip Hvidthøft Delff; Iversen, Anne; Madsen, Henrik;
2014-01-01
time of day, and by use of a filter of the observations it is able to capture per-employee sequence dynamics. Simulations using this method are compared with simulations using homogeneous Markov chains and show far better ability to reproduce key properties of the data. The method is based on...... inhomogeneous Markov chains with where the transition probabilities are estimated using generalized linear models with polynomials, B-splines, and a filter of passed observations as inputs. For treating the dispersion of the data series, a hierarchical model structure is used where one model is for low presence...
Accurate determination of phase arrival times using autoregressive likelihood estimation
G. Kvaerna
1994-06-01
Full Text Available We have investigated the potential automatic use of an onset picker based on autoregressive likelihood estimation. Both a single component version and a three component version of this method have been tested on data from events located in the Khibiny Massif of the Kola peninsula, recorded at the Apatity array, the Apatity three component station and the ARCESS array. Using this method, we have been able to estimate onset times to an accuracy (standard deviation of about 0.05 s for P-phases and 0.15 0.20 s for S phases. These accuracies are as good as for analyst picks, and are considerably better than the accuracies of the current onset procedure used for processing of regional array data at NORSAR. In another application, we have developed a generic procedure to reestimate the onsets of all types of first arriving P phases. By again applying the autoregressive likelihood technique, we have obtained automatic onset times of a quality such that 70% of the automatic picks are within 0.1 s of the best manual pick. For the onset time procedure currently used at NORSAR, the corresponding number is 28%. Clearly, automatic reestimation of first arriving P onsets using the autoregressive likelihood technique has the potential of significantly reducing the retiming efforts of the analyst.
IDENTIFICATION OF PERIODIC AUTOREGRESSIVE MOVING-AVERAGE TIME SERIES MODELS WITH R
Hazem I. El Shekh Ahmed
2014-01-01
Full Text Available Periodic autoregressive moving average PARMA process extend the classical autoregressive moving average ARMA process by allowing the parameters to vary with seasons. Model identification is the identification of a possible model based on an available realization, i.e., determining the type of the model with appropriate orders. The Periodic Autocorrelation Function (PeACF and the Periodic Partial Autocorrelation Function (PePACF serve as useful indicators of the correlation or of the dependence between the values of the series so that they play an important role in model identification. The identification is based on the cut-off property of the Periodic Autocorrelation Function (PeACF. We derive an explicit expression for the asymptotic variance of the sample PeACF to be used in establishing its bands. Therefore, we will get in this study a new structure of the periodic autocorrelation function which depends directly to the variance that will derived to be used in establishing its bands for the PMA process over the cut-off region and we have studied the theoretical side and we will apply some simulated examples with R which agrees well with the theoretical results.
Simulation of M/M/m Queuing Model Based on Markov State Transition Process%基于马尔科夫状态转移过程的M/M/m排队模型仿真
曹永荣; 韩瑞霞; 胡伟
2012-01-01
马尔科夫链是研究排队系统的主要方法,本文在现有M/M/m排队理论和排队系统仿真理论基础上,利用Matlab建立基于马尔科夫状态转移过程的M/M/m排队模型仿真程序.仿真程序在产生初始化参数设定后,利用时钟推进法来模拟空闲服务台和繁忙服务台情况下的服务流程,最后通过M/M/m模型特征描述的仿真计算,获得平均等待时间(E[W])、平均停机时间(E[ DT])、平均排队队长E[ Q]、系统中的平均客户数(E[L])和可能延迟的概率((Ⅱ))5项重要的特征描述.模拟次数设定为20 000次,模拟客户服务率和客户到达率相同,服务台在3～6个的排队系统,并将仿真结果与理论值以及Queue2.0的模拟结果相比较.最终结果显示E[W]、[DT]和H3项最重要指标的仿真结果和理论值都极为相近,误差范围小,本研究将为优先权排队系统的仿真研究提供理论依据.%Markov chain is the main method for the study of queuing systems. This paper integrates the existing theories of M/M/m queuing system and theories of queuing system simulation, and builds simulation program of M/M/m Queuing Model according to the Markov state transition process using Matlab. The simulation process is as follows. First of all, simulation program initializes the parameter settings, such as service time, the interval of customer arrival, the number of server etc. Secondly, promotes the program used time clock which is based on the arrival time of customers and the end time of service. Thirdly, simulates the free servers and busy servers process when a customer arrived, and recodes the corresponding data. Finally, calculate the M/M/m model's characterized descriptions , included in the average down time (E[ DT] ) , the average waiting time (E[ W]), the average number of queuing customer (E[(Q])＞ the average number of customers in the queuing system( E[ L]) and delay probability (Ⅱ) , based on the simulation formula. Sets the
Stability of Markov regenerative switched linear systems
Ogura, Masaki; Preciado, Victor M.
2015-01-01
In this paper, we give a necessary and sufficient condition for mean stability of switched linear systems having a Markov regenerative process as its switching signal. This class of switched linear systems, which we call Markov regenerative switched linear systems, contains Markov jump linear systems and semi-Markov jump linear systems as special cases. We show that a Markov regenerative switched linear system is $m$th mean stable if and only if a particular matrix is Schur stable, under the ...
Entropy: The Markov Ordering Approach
Gorban, A N; Judge, G
2010-01-01
The focus of this article is on entropy and Markov processes. We study the properties of functionals which are invariant with respect to monotonic transformations and analyze two invariant "additivity" properties: (i) existence of a monotonic transformation which makes the functional additive with respect to the joining of independent systems and (ii) existence of a monotonic transformation which makes the functional additive with respect to the partitioning of the space of states. All Lyapunov functionals for Markov chains which have properties (i) and (ii) are derived. We describe the most general ordering of the distribution space, with respect to which all continuous-time Markov processes are monotonic (the {\\em Markov order}). The solution differs significantly from the ordering given by the inequality of entropy growth. For inference, this approach results in a convex compact set of conditionally "most random" distributions.
Raberto, Marco; Scalas, Enrico
2011-01-01
In this paper, we outline a model of graph (or network) dynamics based on two ingredients. The first ingredient is a Markov chain on the space of possible graphs. The second ingredient is a semi-Markov counting process of renewal type. The model consists in subordinating the Markov chain to the semi-Markov counting process. In simple words, this means that the chain transitions occur at random time instants called epochs. The model is quite rich and its possible connections with algebraic geometry are briefly discussed. Moreover, for the sake of simplicity, we focus on the space of undirected graphs with a fixed number of nodes. However, in an example, we present an interbank market model where it is meaningful to use directed graphs or even weighted graphs.
Bibliometric Application of Markov Chains.
Pao, Miranda Lee; McCreery, Laurie
1986-01-01
A rudimentary description of Markov Chains is presented in order to introduce its use to describe and to predict authors' movements among subareas of the discipline of ethnomusicology. Other possible applications are suggested. (Author)
Reviving Markov processes and applications
In this dissertation we study a procedure which restarts a Markov process when the process is killed by some arbitrary multiplicative functional. The regenerative nature of this revival procedure is characterized through a Markov renewal equation. An interesting duality between the revival procedure and the classical killing operation is found. Under the condition that the multiplicative functional possesses an intensity, the generators of the revival process can be written down explicitly. An intimate connection is also found between the perturbation of the sample path of a Markov process and the perturbation of a generator (in Kato's sense). The applications of the theory include the study of the processes like piecewise-deterministic Markov process, virtual waiting time process and the first entrance decomposition (taboo probability)
One-Dimensional Markov Random Fields, Markov Chains and Topological Markov Fields
Chandgotia, N; G. Han; Marcus, B; Meyerovitch, T; Pavlov, R
2014-01-01
In this paper we show that any one-dimensional stationary, finite-valued Markov Random Field (MRF) is a Markov chain, without any mixing condition or condition on the support. Our proof makes use of two properties of the support $X$ of a finite-valued stationary MRF: 1) $X$ is non-wandering (this is a property of the support of any finite-valued stationary process) and 2) $X$ is a topological Markov field (TMF). The latter is a new property that sits in between the classes of shifts of finite...
A Markov Chain Estimator of Multivariate Volatility from High Frequency Data
Hansen, Peter Reinhard; Horel, Guillaume; Lunde, Asger; Archakov, Ilya
We introduce a multivariate estimator of financial volatility that is based on the theory of Markov chains. The Markov chain framework takes advantage of the discreteness of high-frequency returns. We study the finite sample properties of the estimation in a simulation study and apply it to...
D. G. Partridge
2011-07-01
Full Text Available This paper presents a novel approach to investigate cloud-aerosol interactions by coupling a Markov Chain Monte Carlo (MCMC algorithm to a pseudo-adiabatic cloud parcel model. Despite the number of numerical cloud-aerosol sensitivity studies previously conducted few have used statistical analysis tools to investigate the sensitivity of a cloud model to input aerosol physiochemical parameters. Using synthetic data as observed values of cloud droplet number concentration (CDNC distribution, this inverse modelling framework is shown to successfully converge to the correct calibration parameters.
The employed analysis method provides a new, integrative framework to evaluate the sensitivity of the derived CDNC distribution to the input parameters describing the lognormal properties of the accumulation mode and the particle chemistry. To a large extent, results from prior studies are confirmed, but the present study also provides some additional insightful findings. There is a clear transition from very clean marine Arctic conditions where the aerosol parameters representing the mean radius and geometric standard deviation of the accumulation mode are found to be most important for determining the CDNC distribution to very polluted continental environments (aerosol concentration in the accumulation mode >1000 cm^{−3} where particle chemistry is more important than both number concentration and size of the accumulation mode.
The competition and compensation between the cloud model input parameters illustrate that if the soluble mass fraction is reduced, both the number of particles and geometric standard deviation must increase and the mean radius of the accumulation mode must increase in order to achieve the same CDNC distribution.
For more polluted aerosol conditions, with a reduction in soluble mass fraction the parameter correlation becomes weaker and more non-linear over the range of possible solutions
Markov chain modelling of pitting corrosion in underground pipelines
Caleyo, F. [Departamento de Ingenieri' a Metalurgica, ESIQIE, IPN, UPALM Edif. 7, Zacatenco, Mexico D. F. 07738 (Mexico)], E-mail: fcaleyo@gmail.com; Velazquez, J.C. [Departamento de Ingenieri' a Metalurgica, ESIQIE, IPN, UPALM Edif. 7, Zacatenco, Mexico D. F. 07738 (Mexico); Valor, A. [Facultad de Fisica, Universidad de La Habana, San Lazaro y L, Vedado, 10400 La Habana (Cuba); Hallen, J.M. [Departamento de Ingenieri' a Metalurgica, ESIQIE, IPN, UPALM Edif. 7, Zacatenco, Mexico D. F. 07738 (Mexico)
2009-09-15
A continuous-time, non-homogenous linear growth (pure birth) Markov process has been used to model external pitting corrosion in underground pipelines. The closed form solution of Kolmogorov's forward equations for this type of Markov process is used to describe the transition probability function in a discrete pit depth space. The identification of the transition probability function can be achieved by correlating the stochastic pit depth mean with the deterministic mean obtained experimentally. Monte-Carlo simulations previously reported have been used to predict the time evolution of the mean value of the pit depth distribution for different soil textural classes. The simulated distributions have been used to create an empirical Markov chain-based stochastic model for predicting the evolution of pitting corrosion depth and rate distributions from the observed properties of the soil. The proposed model has also been applied to pitting corrosion data from pipeline repeated in-line inspections and laboratory immersion experiments.
Markov chain modelling of pitting corrosion in underground pipelines
A continuous-time, non-homogenous linear growth (pure birth) Markov process has been used to model external pitting corrosion in underground pipelines. The closed form solution of Kolmogorov's forward equations for this type of Markov process is used to describe the transition probability function in a discrete pit depth space. The identification of the transition probability function can be achieved by correlating the stochastic pit depth mean with the deterministic mean obtained experimentally. Monte-Carlo simulations previously reported have been used to predict the time evolution of the mean value of the pit depth distribution for different soil textural classes. The simulated distributions have been used to create an empirical Markov chain-based stochastic model for predicting the evolution of pitting corrosion depth and rate distributions from the observed properties of the soil. The proposed model has also been applied to pitting corrosion data from pipeline repeated in-line inspections and laboratory immersion experiments.
Markov-switching model for nonstationary runoff conditioned on El Niño information
Gelati, E.; Madsen, H.; Rosbjerg, D.
2010-02-01
We define a Markov-modulated autoregressive model with exogenous input (MARX) to generate runoff scenarios using climatic information. Runoff parameterization is assumed to be conditioned on a hidden climate state following a Markov chain, where state transition probabilities are functions of the climatic input. MARX allows stochastic modeling of nonstationary runoff, as runoff anomalies are described by a mixture of autoregressive models with exogenous input, each one corresponding to a climate state. We apply MARX to inflow time series of the Daule Peripa reservoir (Ecuador). El Niño-Southern Oscillation (ENSO) information is used to condition runoff parameterization. Among the investigated ENSO indexes, the NINO 1+2 sea surface temperature anomalies and the trans-Niño index perform best as predictors. In the perspective of reservoir optimization at various time scales, MARX produces realistic long-term scenarios and short-term forecasts, especially when intense El Niño events occur. Low predictive ability is found for negative runoff anomalies, as no climatic index correlating properly with negative inflow anomalies has yet been identified.
郜红娟; 许丽君
2015-01-01
【目的】为探讨快速发展的山区未来土地利用变化规律。【方法】利用 CA-Markov 模型，以贵州省麻江县为例，利用1992年、2002年和2012年三期土地利用数据，模拟了2022年土地利用格局，并分析了土地利用格局演变特点。【结果】结果表明：到2022年研究区耕地、未利用地、草地不断下降，而林地、建设用地和水域将持续增加。耕地、林地、草地和未利用地破碎化下降，建设用地破碎度增加，水域破碎度变化不大；耕地、林地、草地、建设用地的景观形状趋于规则化，而未利用地景观形状复杂化增强，水域景观形状复杂性变化不大；除未利用地聚合度下降外，其他地类聚合度都呈增加趋势。研究区景观破碎度降低；景观形状复杂性下降，各景观类型面积比重不断趋于均衡化，聚集度增强。【结论】该模型对山区土地利用模拟具有较高精度，研究结果可为土地优化研究奠定基础。%Objective]In order to discuss the change of the future land-use in the mountainous re-gion of rapid development.[Method]Taking Majiang County of Guizhou province as the study area,in this paper we simulated the land use pattern in 2022 based on the land use data in 1992, 2002 and 2012,and then analyzed the evolution characteristics of the land use pattern using the CA-Markov model.[Results]The results show that:cultivated land,unused land,grassland of the study area in 2022 will decline,while woodland,construction land and water body will in-crease.Concerning the landscape fragmentation,cultivated land,woodland,grassland and unused land will decrease,while construction land will increase,but the water body has a little change. LSI of cultivated land,woodland,grassland,construction land tend to be in regularization,while LSI of unused land will become more complex,but LSI of water body has a little change.AI of all the land use types will increase
We extend the concept of half life of an Ornstein–Uhlenbeck process to Lévy-driven continuous-time autoregressive moving average processes with stochastic volatility. The half life becomes state dependent, and we analyze its properties in terms of the characteristics of the process. An empirical example based on daily temperatures observed in Petaling Jaya, Malaysia, is presented, where the proposed model is estimated and the distribution of the half life is simulated. The stationarity of the dynamics yield futures prices which asymptotically tend to constant at an exponential rate when time to maturity goes to infinity. The rate is characterized by the eigenvalues of the dynamics. An alternative description of this convergence can be given in terms of our concept of half life. - Highlights: • The concept of half life is extended to Levy-driven continuous time autoregressive moving average processes • The dynamics of Malaysian temperatures are modeled using a continuous time autoregressive model with stochastic volatility • Forward prices on temperature become constant when time to maturity tends to infinity • Convergence in time to maturity is at an exponential rate given by the eigenvalues of the model temperature model
Gaussian Markov random fields theory and applications
Rue, Havard
2005-01-01
Gaussian Markov Random Field (GMRF) models are most widely used in spatial statistics - a very active area of research in which few up-to-date reference works are available. This is the first book on the subject that provides a unified framework of GMRFs with particular emphasis on the computational aspects. This book includes extensive case-studies and, online, a c-library for fast and exact simulation. With chapters contributed by leading researchers in the field, this volume is essential reading for statisticians working in spatial theory and its applications, as well as quantitative researchers in a wide range of science fields where spatial data analysis is important.
Lopez, Gerardo; Favreau, Romeo; Smith, Colin; Costes, Evelyne; Prusinkiewicz, Premyslaw; DeJong, Theodore M.
2008-01-01
International audience L-PEACH is an L-system-based functional-structural model for simulating architectural growth and carbohydrate partitioning among individual organs in peach ( Prunus persica (L.) Batsch) trees. The original model provided a prototype for how tree architecture and carbon economy could be integrated but did not simulate peach tree architecture realistically. Moreover, evaluation of the functional characteristics of the individual organs and the whole-tree remained a lar...
State-feedback stabilization of Markov jump linear systems with randomly observed Markov states
Ogura, Masaki; Cetinkaya, Ahmet
2014-01-01
In this paper we study the state-feedback stabilization of a discrete-time Markov jump linear system when the observation of the Markov chain of the system, called the Markov state, is time-randomized by another Markov chain. Embedding the Markov state into an extended Markov chain, we transform the given system with time-randomized observations to another one having the enlarged Markov-state space but with so-called cluster observations of Markov states. Based on this transformation we propo...
Constructing Dynamic Event Trees from Markov Models
In the probabilistic risk assessment (PRA) of process plants, Markov models can be used to model accurately the complex dynamic interactions between plant physical process variables (e.g., temperature, pressure, etc.) and the instrumentation and control system that monitors and manages the process. One limitation of this approach that has prevented its use in nuclear power plant PRAs is the difficulty of integrating the results of a Markov analysis into an existing PRA. In this paper, we explore a new approach to the generation of failure scenarios and their compilation into dynamic event trees from a Markov model of the system. These event trees can be integrated into an existing PRA using software tools such as SAPHIRE. To implement our approach, we first construct a discrete-time Markov chain modeling the system of interest by: (a) partitioning the process variable state space into magnitude intervals (cells), (b) using analytical equations or a system simulator to determine the transition probabilities between the cells through the cell-to-cell mapping technique, and, (c) using given failure/repair data for all the components of interest. The Markov transition matrix thus generated can be thought of as a process model describing the stochastic dynamic behavior of the finite-state system. We can therefore search the state space starting from a set of initial states to explore all possible paths to failure (scenarios) with associated probabilities. We can also construct event trees of arbitrary depth by tracing paths from a chosen initiating event and recording the following events while keeping track of the probabilities associated with each branch in the tree. As an example of our approach, we use the simple level control system often used as benchmark in the literature with one process variable (liquid level in a tank), and three control units: a drain unit and two supply units. Each unit includes a separate level sensor to observe the liquid level in the tank
马蕾; 罗建强; 黄克己; 叶瑞
2012-01-01
According to the leap characteristics of technical innovation diffusion,the influence of random factors is researched,and the technical diffusion model of technical innovation diffusion process is constructed based on the Markov chain.The simulation result of the diffusion model indicates that the expectation m（t） will be less,finally tend to zero,which along with the diffusion rate and the increase of number of within the industry enterprises,the magnitude of m（t） drop curve is bigger.Finally the technical innovation diffusion is prospected.%针对技术创新扩散呈现出来的跳跃性特点,研究了随机因素对技术创新扩散活动的影响,构建了基于Markov链的技术创新扩散模型,并对这一扩散模型进行仿真分析,结果发现,随着时间的推移,未采纳新技术的企业的期望值m（t）会越少,最后趋向于零,其中随着扩散率和行业内企业数目的增加,m（t）曲线下降的幅度越大。最后对技术创新扩散可拓展的研究方向进行了展望。
Data-driven Markov models and their application in the evaluation of adverse events in radiotherapy
Abler, Daniel; Davies, Jim; Dosanjh, Manjit; Jena, Raj; Kirkby, Norman; Peach, Ken
2013-01-01
Decision-making processes in medicine rely increasingly on modelling and simulation techniques; they are especially useful when combining evidence from multiple sources. Markov models are frequently used to synthesize the available evidence for such simulation studies, by describing disease and treatment progress, as well as associated factors such as the treatment's effects on a patient's life and the costs to society. When the same decision problem is investigated by multiple stakeholders, differing modelling assumptions are often applied, making synthesis and interpretation of the results difficult. This paper proposes a standardized approach towards the creation of Markov models. It introduces the notion of ‘general Markov models’, providing a common definition of the Markov models that underlie many similar decision problems, and develops a language for their specification. We demonstrate the application of this language by developing a general Markov model for adverse event analysis in radiotherapy ...
CLARK, Todd E.; Francesco Ravazzolo
2012-01-01
This paper compares alternative models of time-varying macroeconomic volatility on the basis of the accuracy of point and density forecasts of macroeconomic variables. In this analysis, we consider both Bayesian autoregressive and Bayesian vector autoregressive models that incorporate some form of time-varying volatility, precisely stochastic volatility (both with constant and time-varying autoregressive coeffi cients), stochastic volatility following a stationary AR process, stochastic volat...
On Markov parameters in system identification
Phan, Minh; Juang, Jer-Nan; Longman, Richard W.
1991-01-01
A detailed discussion of Markov parameters in system identification is given. Different forms of input-output representation of linear discrete-time systems are reviewed and discussed. Interpretation of sampled response data as Markov parameters is presented. Relations between the state-space model and particular linear difference models via the Markov parameters are formulated. A generalization of Markov parameters to observer and Kalman filter Markov parameters for system identification is explained. These extended Markov parameters play an important role in providing not only a state-space realization, but also an observer/Kalman filter for the system of interest.
Highlights: • An unsupervised clustering algorithm with a neural network model was explored. • The forecasting results of solar radiation time series and the comparison of their performance was simulated. • A new method was proposed combining k-means algorithm and NAR network to provide better prediction results. - Abstract: In this paper, we review our work for forecasting hourly global horizontal solar radiation based on the combination of unsupervised k-means clustering algorithm and artificial neural networks (ANN). k-Means algorithm focused on extracting useful information from the data with the aim of modeling the time series behavior and find patterns of the input space by clustering the data. On the other hand, nonlinear autoregressive (NAR) neural networks are powerful computational models for modeling and forecasting nonlinear time series. Taking the advantage of both methods, a new method was proposed combining k-means algorithm and NAR network to provide better forecasting results
Goodness-of-fit tests for vector autoregressive models in time series
无
2010-01-01
The paper proposes and studies some diagnostic tools for checking the goodness-of-fit of general parametric vector autoregressive models in time series. The resulted tests are asymptotically chi-squared under the null hypothesis and can detect the alternatives converging to the null at a parametric rate. The tests involve weight functions,which provides us with the flexibility to choose scores for enhancing power performance,especially under directional alternatives. When the alternatives are not directional,we construct asymptotically distribution-free maximin tests for a large class of alternatives. A possibility to construct score-based omnibus tests is discussed when the alternative is saturated. The power performance is also investigated. In addition,when the sample size is small,a nonparametric Monte Carlo test approach for dependent data is proposed to improve the performance of the tests. The algorithm is easy to implement. Simulation studies and real applications are carried out for illustration.
Chon, K H; Hoyer, D; Armoundas, A A; Holstein-Rathlou, N H; Marsh, D J
1999-01-01
In this study, we introduce a new approach for estimating linear and nonlinear stochastic autoregressive moving average (ARMA) model parameters, given a corrupt signal, using artificial recurrent neural networks. This new approach is a two-step approach in which the parameters of the deterministic...... part of the stochastic ARMA model are first estimated via a three-layer artificial neural network (deterministic estimation step) and then reestimated using the prediction error as one of the inputs to the artificial neural networks in an iterative algorithm (stochastic estimation step). The prediction...... error is obtained by subtracting the corrupt signal of the estimated ARMA model obtained via the deterministic estimation step from the system output response. We present computer simulation examples to show the efficacy of the proposed stochastic recurrent neural network approach in obtaining accurate...
AN EXPONENTIAL INEQUALITY FOR AUTOREGRESSIVE PROCESSES IN ADAPTIVE TRACKING
Bernard BERCU
2007-01-01
A wide range of literature concerning classical asymptotic properties for linear models with adaptive control is available, such as strong laws of large numbers or central limit theorems.Unfortunately, in contrast with the situation without control, it appears to be impossible to find sharp asymptotic or nonasymptotic properties such as large deviation principles or exponential inequalities.Our purpose is to provide a first step towards that direction by proving a very simple exponential inequality for the standard least squares estimator of the unknown parameter of Gaussian autoregressive process in adaptive tracking.
Temporal aggregation in first order cointegrated vector autoregressive
La Cour, Lisbeth Funding; Milhøj, Anders
2006-01-01
We study aggregation - or sample frequencies - of time series, e.g. aggregation from weekly to monthly or quarterly time series. Aggregation usually gives shorter time series but spurious phenomena, in e.g. daily observations, can on the other hand be avoided. An important issue is the effect of ...... aggregation on the adjustment coefficient in cointegrated systems. We study only first order vector autoregressive processes for n dimensional time series Xt, and we illustrate the theory by a two dimensional and a four dimensional model for prices of various grades of gasoline....
Temporal aggregation in first order cointegrated vector autoregressive models
La Cour, Lisbeth Funding; Milhøj, Anders
We study aggregation - or sample frequencies - of time series, e.g. aggregation from weekly to monthly or quarterly time series. Aggregation usually gives shorter time series but spurious phenomena, in e.g. daily observations, can on the other hand be avoided. An important issue is the effect of ...... aggregation on the adjustment coefficient in cointegrated systems. We study only first order vector autoregressive processes for n dimensional time series Xt, and we illustrate the theory by a two dimensional and a four dimensional model for prices of various grades of gasoline...
Accurate determination of phase arrival times using autoregressive likelihood estimation
G. Kvaerna
1994-01-01
We have investigated the potential automatic use of an onset picker based on autoregressive likelihood estimation. Both a single component version and a three component version of this method have been tested on data from events located in the Khibiny Massif of the Kola peninsula, recorded at the Apatity array, the Apatity three component station and the ARCESS array. Using this method, we have been able to estimate onset times to an accuracy (standard deviation) of about 0.05 s for P-phases ...
Analysis of nonlinear systems using ARMA [autoregressive moving average] models
While many vibration systems exhibit primarily linear behavior, a significant percentage of the systems encountered in vibration and model testing are mildly to severely nonlinear. Analysis methods for such nonlinear systems are not yet well developed and the response of such systems is not accurately predicted by linear models. Nonlinear ARMA (autoregressive moving average) models are one method for the analysis and response prediction of nonlinear vibratory systems. In this paper we review the background of linear and nonlinear ARMA models, and illustrate the application of these models to nonlinear vibration systems. We conclude by summarizing the advantages and disadvantages of ARMA models and emphasizing prospects for future development. 14 refs., 11 figs