The Annals of Statistics

A Note on Selecting Parametric Models in Bayesian Inference

William S. Krasker

Full-text: Open access

Abstract

This note is concerned with how to replace assessment of a "true" prior on a nonparametric family of distributions--which is usually infeasible--by assessment of an approximating prior with support in a parametrized subfamily, in such a way that the posterior derived from the parametric model is close to the "true" posterior. In general it is not sufficient that the approximating prior be close to the true prior in the sense of weak convergence, and we characterize the additional aspect of the true prior that must be considered explicitly.

Article information

Source
Ann. Statist., Volume 12, Number 2 (1984), 751-757.

Dates
First available in Project Euclid: 12 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1176346521

Digital Object Identifier
doi:10.1214/aos/1176346521

Mathematical Reviews number (MathSciNet)
MR740927

Zentralblatt MATH identifier
0544.62049

JSTOR
links.jstor.org

Subjects
Primary: 62G99: None of the above, but in this section
Secondary: 62A15

Keywords
Nonparametric Bayes models parametric models Bayesian inference approximation of priors

Citation

Krasker, William S. A Note on Selecting Parametric Models in Bayesian Inference. Ann. Statist. 12 (1984), no. 2, 751--757. doi:10.1214/aos/1176346521. https://projecteuclid.org/euclid.aos/1176346521


Export citation