Accession Number:

ADA255991

Title:

An Iterative Monte Carlo Method for Nonconjugate Bayesian Analysis

Descriptive Note:

Technical rept.

Corporate Author:

STANFORD UNIV CA DEPT OF STATISTICS

Personal Author(s):

Report Date:

1992-09-07

Pagination or Media Count:

28.0

Abstract:

The Gibbs sampler has been proposed as a general method for Bayesian calculation in Gelfand and Smith 1990. However experience to date is almost exclusively in applications assuming conjugacy where implementation is reasonably straightforward. This paper describes a tailored rejection method approach for implementation of the Gibbs sampler when nonconjugate structure is present. Several challenging applications are presented for illustration.

Subject Categories:

  • Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE