Statistics and Computing

, Volume 12, Issue 1, pp 27–36 | Cite as

On Bayesian model and variable selection using MCMC

  • Petros Dellaportas
  • Jonathan J. Forster
  • Ioannis Ntzoufras

Abstract

Several MCMC methods have been proposed for estimating probabilities of models and associated 'model-averaged' posterior distributions in the presence of model uncertainty. We discuss, compare, develop and illustrate several of these methods, focussing on connections between them.

Gibbs sampler independence sampler Metropolis–Hastings reversible jump 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Besag J. 1997. Comment on 'On Bayesian analysis of mixtures with an unknown number of components'. Journal of Royal Statistical Society B 59: p. 774.Google Scholar
  2. Carlin B.P. and Chib S. 1995. Bayesian model choice via Markov chain Monte Carlo methods. Journal of Royal Statistical Society B 157: 473-484.Google Scholar
  3. Chipman H. 1996. Bayesian variable selection with related predictors.Canadian Journal of Statistics 24: 17-36.Google Scholar
  4. Clyde M. and DeSimone-Sasinowska H. 1998. Accounting for model uncertainty in Poisson regression models: Does particulate matter particularly matter? Institute of Statistics and Decision Sciences, Duke University, Technical Report 97-06.Google Scholar
  5. Dellaportas P. and Forster J.J. 1999. Markov chain Monte Carlo model determination for hierarchical and graphical log-linear models.Biometrika 86: 615-633.Google Scholar
  6. Dellaportas P. and Smith A.F.M. 1993. Bayesian inference for generalised linear and proportional hazards models via Gibbs sampling. Applied Statistics 42: 443-459.Google Scholar
  7. George E. and McCulloch R.E. 1993. Variable selection via Gibbs sampling. Journal of the American Statistical Association 88: 881-889.Google Scholar
  8. Godsill S.J. 1998. On the relationship between MCMC model uncertainty methods. Signal Processing Group, Cambridge University Engineering Department, Technical Report.Google Scholar
  9. Green P. 1995. Reversible jump Markov chain Monte Carlo computation and Bayesian model determination. Biometrika 82: 711-732.Google Scholar
  10. Green P. and O'Hagan A. 1998. Model choice with MCMC on product spaces without using pseudopriors. Department of Mathematics, University of Nottingham, Technical Report.Google Scholar
  11. Gruet M.-A. and Robert C. 1997. Comment on 'On Bayesian analysis of mixtures with an unknown number of components'. Journal of Royal Statistical Society B 59: p. 777.Google Scholar
  12. Healy M.J.R. 1988. Glim: An Introduction. Claredon Press, UK.Google Scholar
  13. Kuo L. and Mallick B. 1998. Variable selection for regression models.Sankhyā, B 60: 65-81.Google Scholar
  14. Madigan D. and York J. 1995. Bayesian graphical models for discrete data. International Statistical Review 63: 215-232.Google Scholar
  15. Raftery A.E. 1996. Approximate bayes factors and accounting for model uncertainty in generalised linear models. Biometrika 83: 251-266.Google Scholar
  16. Raftery A.E., Madigan D., and Hoeting J.A. 1997. Bayesian model averaging for linear regression models. Journal of the American Statistical Association 92: 179-191.Google Scholar
  17. Richardson S. and Green P.J. 1997. On Bayesian analysis of mixtures with an unknown number of components (with discussion).Journal of Royal Statistical Society B 59: 731-792.Google Scholar
  18. Roberts G.O. 1996. Markov chain concepts related to sampling algorithms.In: Gilks W.R., Richardson S., and Spiegelhalter D.J.(Eds.), Markov Chain Monte Carlo in Practice. Chapman and Hall, London, pp. 45-57.Google Scholar
  19. Tierney L. 1994. Markov chains for exploring posterior distributions (with discussion). Annals of Statistics 22: 1701-1762.Google Scholar

Copyright information

© Kluwer Academic Publishers 2002

Authors and Affiliations

  • Petros Dellaportas
  • Jonathan J. Forster
  • Ioannis Ntzoufras

There are no affiliations available

Personalised recommendations