Journal of the Korean Statistical Society

The Korean Statistical Society (한국통계학회)
권호 표지

Variable Selection in Linear Random Effects Models for Normal Data

  • Kim, Hea-Jung (Department of Statistics, College of Natural Science, Dongguk University)
  • Published : 1998.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper is concerned with selecting covariates to be included in building linear random effects models designed to analyze clustered response normal data. It is based on a Bayesian approach, intended to propose and develop a procedure that uses probabilistic considerations for selecting premising subsets of covariates. The approach reformulates the linear random effects model in a hierarchical normal and point mass mixture model by introducing a set of latent variables that will be used to identify subset choices. The hierarchical model is flexible to easily accommodate sign constraints in the number of regression coefficients. Utilizing Gibbs sampler, the appropriate posterior probability of each subset of covariates is obtained. Thus, In this procedure, the most promising subset of covariates can be identified as that with highest posterior probability. The procedure is illustrated through a simulation study.

Keywords

References

  1. Annals of Institute of Statistical Mathe-matics v.43 Bayesian image restoration, with two applications in spatial statistics Besag, J. E.;York, J.;Mollie
  2. CODA;Convergence diagnosis and output analysis software for Gibbs sampling output version 0.30 Best, N.;Cowles, M. K.;Vines, K.
  3. Bayesian Analysis of Linear Models Broemeling, L. D.
  4. Journal of the American Statistical Association v.91 Markov chain Monte Carlo convergence diagnostics: a comparative review Cowles, M. K.;Carlin, B. P.
  5. Non-uniform random generation Devroye, L.
  6. IEEE Transation Pattern Anal-ysis and Machine Intelligence v.6 Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images Geman, S.;Geman, D.
  7. Bayesian Statistics 5, Ed. Variable selection and model comparison in regression Geweke, J.;Bernardo, J. M.;Berger, J. O.;Dawid, A. P.;Smith, A. F. M.
  8. Journal of the American Statistical Association v.91 The effect of improper priors on Gibbs sampling in hierarchical linear mixed models Hobert, J. P.;Gasella, G.
  9. Longitudinal Data with Serial Correlation: A State Space Approach Jonse, R. H.
  10. Biometrics v.38 Random effects models for longitudinal data Laird, N. M.;Ware, J. H.
  11. Biometrics v.44 A Statistical paradox Lindley, D. V.
  12. Journal of the American Statistical Association v.83 Newton-Raphson and EM algorithms for linear mixed-effects models for repeated measure data Lindstrom, M.;Bates, D.
  13. The American Statistician v.51 Linear transformations of linear mixed-effects models Morrell, C. H.;Pearson, J. D.;Brant, L. J.
  14. Estimation of Variance Components and Appli-cations Rao, C.;Kleffe, J.
  15. Journal of the American Statistical Association v.82 The calculation of posterior distributions by data augmentation(with discussion) Tanner, M.;Wang, W.
  16. An-nals of Statistics v.22 Markov chains for exploring posterior distributions Tierney, L.