Inference for nonconjugate Bayesian Models using the Gibbs sampler

Bradley P. Carlin, Nicholas G. Polson

Research output: Contribution to journalArticlepeer-review

91 Scopus citations

Abstract

A Bayesian approach to modeling a rich class of nonconjugate problems is presented. An adaptive Monte Carlo integration technique known as the Gibbs sampler is proposed as a mechanism for implementing a conceptually and computationally simple solution in such a framework. The result is a general strategy for obtaining marginal posterior densities under changing specification of the model error densities and related prior densities. We illustrate the approach in a nonlinear regression setting, comparing the merits of three candidate error distributions.

Original languageEnglish (US)
Pages (from-to)399-405
Number of pages7
JournalCanadian Journal of Statistics
Volume19
Issue number4
DOIs
StatePublished - Dec 1991

Keywords

  • Bayesian model choice
  • Gibbs sampler
  • nonlinear models
  • nonnormal errors

Fingerprint Dive into the research topics of 'Inference for nonconjugate Bayesian Models using the Gibbs sampler'. Together they form a unique fingerprint.

Cite this