Management Science and Financial Engineering

The Korean Operations Research and Management Science Society (한국경영과학회)
권호 표지

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

  • Sung, Min-Je (School of Business Administration, Ajou University)
  • Published : 2006.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

We use the hierarchical Bayesian approach to describe the transition probabilities of a binary nonhomogeneous 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 exchangeabiligy, 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.

Keywords

References

  1. Anderson, T. W. and L. A. Goodman, 'Statistical inference about Markov chains,' Annals of Mathematical Statistics 28 (1957), 89-110 https://doi.org/10.1214/aoms/1177707039
  2. Billingsley, P., 'Statistical Methods in Markov chains,' Annals of Mathematical Statistics 32 (1961), 12-40 https://doi.org/10.1214/aoms/1177705136
  3. Cargnoni, C, P. Mueller, and M. West, 'Bayesian forecasting of multinomial time series through conditionally Gaussian dynamic models,' Journal of American Statistical Association 92 (1997), 640-647 https://doi.org/10.2307/2965711
  4. Chatfield, C, 'Statistical inference regarding Markov chain models,' Applied Statistics 22, 1 (1973), 7-20 https://doi.org/10.2307/2346299
  5. Cox, D. R., 'Statistical analysis of time series: Some recent developments,' Scandinavian Journal of Statistics 8 (1981), 93-115
  6. Erkanli, A., Soyer, R., and A. Angold, 'Bayesian analyses of longitudinal binary data using Markov regression models of unknown order,' Statistics in Medicine 20 (2001), 755-770 https://doi.org/10.1002/sim.702
  7. Gelfand, A. E. and A. F. M. Smith, 'Sampling-based approaches to calculating marginal densities,' Journal of American Statistical Association 85 (1990), 972-985 https://doi.org/10.2307/2289594
  8. Grunwald, G., A. Raftery, and P. Guttorp, 'Time series for continuous proportions,' Journal of the Royal Statistical Society, Ser. B 55 (1993), 103-116
  9. Lee, T.C., G. G. Judge, and A. Zellner, 'Maximum likelihood and Bayesian estimation of transition probabilities,' Journal of American statistical Association 63 (1968), 1162-1179 https://doi.org/10.2307/2285875
  10. Meshkani, M., 'Empirical Bayes estimation of transition probabilities for Markov chains,' Ph.D. Dissertation, Florida State University, 1978
  11. Muenz, L. and L. Rubinstein, 'Markov models for covariate dependence of binary sequences,' Biometrics 41 (1985), 91-101 https://doi.org/10.2307/2530646
  12. Nhan, N., 'Effects and outcome of residential treatment,' Technical report, Graydon Manor Research Department, USA, 1999
  13. Spiegelhalter D., N. Best, B. Carlin, and Van der Linde, 'Bayesian Measures of Model. Complexity and Fit (with Discussion),' Journal of the Royal Statistical Society, Series B 64, 4 (2003), 583-616
  14. Spiegelhalter. D., A. Thomas, N. Best, and W. Gilks, 'Bayesian Inference Using Gibbs Sampling Manual (version ii),' MRC Biostatistics Unit, Cambridge University, UK, 1996