Robust Bayesian Models for Meta-Analysis

  • Kim, Dal-Ho (Department of Statistics, Kyungpook National University) ;
  • Park, Gea-Joo (Department of Statistics, Kyungpook National University)
  • Published : 2000.10.31

Abstract

This article addresses aspects of combining information, with special attention to meta-analysis. In specific, we consider hierarchical Bayesian models for meta-analysis under priors which are scale mixtures of normal, and thus have tail heavier than that of the normal. Numerical methods of finding Bayes estimators under these heavy tailed prior are given, and are illustrated with an actual example.

Keywords

References

  1. Bayesian Inference in Statistical Analysis Box, G. E. P.;Tiao, G. C.
  2. Canadian Journal of Statistics v.19 Inference for nonconjugate Bayesian models using the Gibbs sampler Carlin, B. P.;Polson, N. G.
  3. Controlled Clinical Trials v.7 Meta-analysis in clinical trials DerSimonian, R.;Laired, N.
  4. Statistical Methodology in the Pharmaceutical Sciences Bayesian meta-analysis DuMouchel, W. H.;D. A. Berry(ed.)
  5. Controlled Clinical Trials v.10 Meta-analysis and evidence Goodman, S. N.
  6. Communication in Statistics - Theory and Methods v.20 Gibbs sampling for marginal posterior expectations Gelfand, A. E.;Smith, A. F. M.
  7. Statistical Science v.7 Inference from iterative simulation using multiple sequences Gelman, A.;Rubin, D. B.
  8. Bayesian Statistics 4 Hierarchical models for combining information and for meta-analyses Morris, C. N.;Normand, S. L.;J.M. Bernardo(ed.);J.O. Bernardo(ed.);M.H. DeGroot(ed.);D.V. Lindely(ed.);A.F.M. Smith(ed.)
  9. Bayesian Statistics 3 Modeling with heavy tails O'Hagan, A.;J.M. Bernardo(ed.);M.H. DeGroot(ed.);D.V. Lindely(ed.);A.F.M. Smith(ed.)
  10. Bayesian Statistics 2 Generalized linear models: scale parameters, outlier accommodation and prior distributions West, M.
  11. Biometrika v.74 On scale mixtures of normal distributions West, M.