Bayesian Analysis of Binary Non-homogeneous Markov Chain with Two Different Time Dependent Structures

다국어 초록 (Multilingual Abstract)

We use the hierarchical Bayesian approach to describe the transition probabilities of a binary non-homogeneous Markov chain. The Markov chain is used for describing the transition behavior of emotionally disturbed children in a treatment program. The effects of covariates on transition probabilities are assessed using a logit link function. To describe the time evolution of transition probabilities, we consider two modeling strategies. The first strategy is based on the concept of exchangeability, whereas the second one is based on a first order Markov property. The deviance information criterion (DIC) measure is used to compare models with two different time dependent structures. The inferences are made using the Markov chain Monte Carlo technique. The developed methodology is applied to some real data.

참고문헌 (Reference)

1 "Time series for continuous proportions Journal of the Royal Statistical Society" 103-55 116, 1993

2 "Statistical inference regarding Markov chain models" 22 (22): 7-20, 1973

3 "Statistical inference about Markov chains" 89-110, 1957

4 "Statistical analysis of time series Scandinavian Journal of Statistics 8" 93-115, 1981

5 "Statistical Methods in Markov chains" 32 : 12-40, 1961

6 "Sampling-based approaches to calculating marginal densities Journal of American Statistical Association 85" 972-985, 1990

7 "Maximum likelihood and Bayesian estimation of transition probabilities Journal of American statistical Association 63" 1162-1179, 1968

8 "Markov models for covariate dependence of binary sequences" 41 : 91-101, 1985

9 "Empirical Bayes estimation of transition probabilities for Markov chains" Florida State University 1978

10 "Effects and outcome of residential treatment" Graydon Manor Research Department,USA 1999

11 "Bayesian forecasting of multinomial time series through conditionally Gaussian dynamic models" 92 : 640-647, 1997

12 "Bayesian analyses of longitudinal binary data using Markov regression models of unknown order" 20 : 755-770, 2001

13 "Bayesian Measures of Model Complexity and Fit" 64 (64): 583-616, 2003

14 "Bayesian Inference Using Gibbs Sampling Manual (version ii)" Cambridge University,UK 1996