Distributions of statistics describing concentration of runs in non homogeneous Markov-dependent trials

In the first n, n ? 3, trials of a non homogeneous zero-one Markov chain of first order, we consider runs of ones of length exceeding a threshold. The article deals with statistics denoting, the length and the position of the shortest segment of the chain in which all such runs of ones are concentrated. The study provides recursive schemes for conditional distributions of these statistics. Numerical examples illustrate the theoretical results.     

On runs of length exceeding a threshold: normal approximation

Run statistics denoting number of runs and sum of run lengths are defined on binary sequences and their asymptotic normality is established by a simple unified way for Bernoulli sequences. All the considered statistics share a common feature; they refer to runs of length exceeding a specific length (a threshold). Asymptotic results of associated statistics denoting run lengths and waiting times are derived as well. Specific probabilities of the examined statistics are used in applications in the fields of system reliability and molecular biology. The study is illustrated by an extensive numerical experimentation.     

On the distribution and expectation of success runs in nonhomogeneous Markov dependent trials

The number of success runs for nonhomogeneous markov dependent trials are represented as the sum of Bernoulli trials and the expected value of runs are obtained by using this representation. The distribution and bounds for the distribution of the longest run are derived for markov dependent trials.     

An ARL-unbiased design of time-between-events control charts with runs rules

In this paper, we consider incorporating the runs rules into the cumulative quantity control (CQC) chart for monitoring time-between-events data. We propose a simple and effective procedure to design a CQC chart coupled with runs rules that can yield average run length (ARL)-unbiased performance and meet the required in-control ARL. The proposed design involves determining a relation between the upper side and lower side false alarm probabilities. A Markov chain approach is used to evaluate the ARL performance of various control schemes studied in this paper. An extensive numerical comparison shows that the proposed design approach can result in a significant reduction in ARL for detecting increases in the occurrence rate of the event in comparison with the basic CQC charts.     

On inference from Markov chain macro-data using transforms

We consider data that are longitudinal, arising from n individuals over m time periods. Each individual moves according to the same homogeneous Markov chain, with s states. If the individual sample paths are observed, so that ‘micro-data’ are available, the transition probability matrix is estimated by maximum likelihood straightforwardly from the transition counts. If only the overall numbers in the various states at each time point are observed, we have ‘macro-data’, and the likelihood function is difficult to compute. In that case a variety of methods has been proposed in the literature. In this paper we propose methods based on generating functions and investigate their performance.     

Applying a Markov chain for the stock pricing of a novel forecasting model

In this article, a stock-forecasting model is developed to analyze a company's stock price variation related to the Taiwanese company HTC. The main difference to previous articles is that this study uses the data of the HTC in recent ten years to build a Markov transition matrix. Instead of trying to predict the stock price variation through the traditional approach to the HTC stock problem, we integrate two types of Markov chain that are used in different ways. One is a regular Markov chain, and the other is an absorbing Markov chain. Through a regular Markov chain, we can obtain important information such as what happens in the long run or whether the distribution of the states tends to stabilize over time in an efficient way. Next, we used an artificial variable technique to create an absorbing Markov chain. Thus, we used an absorbing Markov chain to provide information about the period between the increases before arriving at the decreasing state of the HTC stock. We provide investors with information on how long the HTC stock will keep increasing before its price begins to fall, which is extremely important information to them.     

Markov chain models for multivariate repeated binary data analysis

Repeated categorical outcomes frequently occur in clinical trials. Muenz and Rubinstein (1985) presented Markov chain models to analyze binary repeated data in a breast cancer study. We extend their method to the setting when more than one repeated outcome variable is of interest. In a randomized clinical trial of breast cancer, we investigate the dependency of toxicities on predictor variables and the relationship among multiple toxic effects.     

Bayesian inference in hidden Markov models through the reversible jump Markov chain Monte Carlo method

Hidden Markov models form an extension of mixture models which provides a flexible class of models exhibiting dependence and a possibly large degree of variability. We show how reversible jump Markov chain Monte Carlo techniques can be used to estimate the parameters as well as the number of components of a hidden Markov model in a Bayesian framework. We employ a mixture of zero-mean normal distributions as our main example and apply this model to three sets of data from finance, meteorology and geomagnetism.     

Identification-robust moment-based tests for Markov switching in autoregressive models

ABSTRACT

This paper develops tests of the null hypothesis of linearity in the context of autoregressive models with Markov-switching means and variances. These tests are robust to the identification failures that plague conventional likelihood-based inference methods. The approach exploits the moments of normal mixtures implied by the regime-switching process and uses Monte Carlo test techniques to deal with the presence of an autoregressive component in the model specification. The proposed tests have very respectable power in comparison with the optimal tests for Markov-switching parameters of Carrasco et al. (2014 Carrasco, M., Hu, L., Ploberger, W. (2014). Optimal test for Markov switching parameters. Econometrica 82(2):765–784.[Crossref], [Web of Science ®] , [Google Scholar]), and they are also quite attractive owing to their computational simplicity. The new tests are illustrated with an empirical application to an autoregressive model of USA output growth.     

Quotas on runs of successes and failures in a multi-state markov chain

For the time-homogeneous multi-state Markov chain {X_n,n≧0} with states labeled as "0" (success) and "f"(failure), f=1,2,… the waiting time problems to be discussed arise by setting quotas on runs of success and failures. Some particular cases are considered.     

Central Limit Theorem approximations for the number of runs in Markov-dependent binary sequences

We consider Markov-dependent binary sequences and study various types of success runs (overlapping, non-overlapping, exact, etc.) by examining additive functionals based on state visits and transitions in an appropriate Markov chain. We establish a multivariate Central Limit Theorem for the number of these types of runs and obtain its covariance matrix by means of the recurrent potential matrix of the Markov chain. Explicit expressions for the covariance matrix are given in the Bernoulli and a simple Markov-dependent case by expressing the recurrent potential matrix in terms of the stationary distribution and the mean transition times in the chain. We also obtain a multivariate Central Limit Theorem for the joint number of non-overlapping runs of various sizes and give its covariance matrix in explicit form for Markov dependent trials.     

Fitting Markov chain models to discrete state series such as DNA sequences

Discrete state series such as DNA sequences can often be modelled by Markov chains. The analysis of such series is discussed in the context of log-linear models. The data produce contingency tables with similar margins due to the dependence of the observations. However, despite the unusual structure of the tables, the analysis is equivalent to that for data from multinomial sampling. The reason why the standard number of degrees of freedom is correct is explained by using theoretical arguments and the asymptotic distribution of the deviance is verified empirically. Problems involved with fitting high order Markov chain models, such as reduced power and computational expense, are also discussed.     

A simple test for equally likely random responses in a sequence of bernoulli trials

A simple versatile combinatorial test is given for the null hypothesis that the two kinds of responses in a sequence of binary random variables are both equiprobable and randomly distributed. It is sensitive to a preponderance of either kind of response in either of two pre-selected halves of the positions of the sequence, e.g., the right half vs. the left, or the center vs. both ends. It combines the nice features of being, on the one hand, relatively assumption free and easy to apply and, on the other hand, sensitive to basic patterns underlying a poor fit of the empirical distribution to a theoretical model.     

Construction of a Markov Chain with Given Stationary Distribution

Given a rational, finite probability vector, a Markov chain is constructed having the given vector as its stationary distribution.     

Joint coverage probability in a simulation study on continuous-time Markov chain parameter estimation

Parameter dependency within data sets in simulation studies is common, especially in models such as continuous-time Markov chains (CTMCs). Additionally, the literature lacks a comprehensive examination of estimation performance for the likelihood-based general multi-state CTMC. Among studies attempting to assess the estimation, none have accounted for dependency among parameter estimates. The purpose of this research is twofold: (1) to develop a multivariate approach for assessing accuracy and precision for simulation studies (2) to add to the literature a comprehensive examination of the estimation of a general 3-state CTMC model. Simulation studies are conducted to analyze longitudinal data with a trinomial outcome using a CTMC with and without covariates. Measures of performance including bias, component-wise coverage probabilities, and joint coverage probabilities are calculated. An application is presented using Alzheimer's disease caregiver stress levels. Comparisons of joint and component-wise parameter estimates yield conflicting inferential results in simulations from models with and without covariates. In conclusion, caution should be taken when conducting simulation studies aiming to assess performance and choice of inference should properly reflect the purpose of the simulation.     

Application of a non-homogeneous Markov chain with seasonal transition probabilities to ozone data

In this work, we assume that the sequence recording whether or not an ozone exceedance of an environmental threshold has occurred in a given day is ruled by a non-homogeneous Markov chain of order one. In order to account for the possible presence of cycles in the empirical transition probabilities, a parametric form incorporating seasonal components is considered. Results show that even though some covariates (namely, relative humidity and temperature) are not included explicitly in the model, their influence is captured in the behavior of the transition probabilities. Parameters are estimated using the Bayesian point of view via Markov chain Monte Carlo algorithms. The model is applied to ozone data obtained from the monitoring network of Mexico City, Mexico. An analysis of how the methodology could be used as an aid in the decision-making is also given.     

Markov chain Monte Carlo methods for high dimensional inversion in remote sensing

Summary.  We discuss the inversion of the gas profiles (ozone, NO₃, NO₂, aerosols and neutral density) in the upper atmosphere from the spectral occultation measurements. The data are produced by the 'Global ozone monitoring of occultation of stars' instrument on board the Envisat satellite that was launched in March 2002. The instrument measures the attenuation of light spectra at various horizontal paths from about 100 km down to 10–20 km. The new feature is that these data allow the inversion of the gas concentration height profiles. A short introduction is given to the present operational data management procedure with examples of the first real data inversion. Several solution options for a more comprehensive statistical inversion are presented. A direct inversion leads to a non-linear model with hundreds of parameters to be estimated. The problem is solved with an adaptive single-step Markov chain Monte Carlo algorithm. Another approach is to divide the problem into several non-linear smaller dimensional problems, to run parallel adaptive Markov chain Monte Carlo chains for them and to solve the gas profiles in repetitive linear steps. The effect of grid size is discussed, and we present how the prior regularization takes the grid size into account in a way that effectively leads to a grid-independent inversion.     

Trends in smoking cessation: a Markov model approach

Intervention trials such as studies on smoking cessation may observe multiple, discrete outcomes over time. When the outcome is binary, participant observations may alternate between two states over the course of the study. The generalized estimating equation (GEE) approach is commonly used to analyze binary, longitudinal data in the context of independent variables. However, the sequence of observations may be assumed to follow a Markov chain with stationary transition probabilities when observations are made at fixed time points. Participants favoring the transition to one particular state over the other would be evidence of a trend in the observations. Using a log-transformed trend parameter, the determinants of a trend in a binary, longitudinal study may be evaluated by maximizing the likelihood function. A new methodology is presented here to test for the presence and determinants of a trend in binary, longitudinal observations. Empirical studies are evaluated and comparisons are made with the GEE approach. Practical application of the proposed method is made to the data available from an intervention study on smoking cessation.     

Parallel discretization of the Markov chain approximation for the autoregressive moving average chart

Abstract

In the Markov chain model of an autoregressive moving average chart, the post-transition states of nonzero transition probabilities are distributed along one-dimensional lines of a constant gradient over the state space. By considering this characteristic, we propose discretizing the state space parallel to the gradient of these one-dimensional lines. We demonstrate that our method substantially reduces the computational cost of the Markov chain approximation for the average run length in two- and three-dimensional state spaces. Also, we investigate the effect of these one-dimensional lines on the computational cost. Lastly, we generalize our method to state spaces larger than three dimensions.