Translator Disclaimer
June, 1984 A Note on Selecting Parametric Models in Bayesian Inference
William S. Krasker
Ann. Statist. 12(2): 751-757 (June, 1984). DOI: 10.1214/aos/1176346521

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.

Citation

Download Citation

William S. Krasker. "A Note on Selecting Parametric Models in Bayesian Inference." Ann. Statist. 12 (2) 751 - 757, June, 1984. https://doi.org/10.1214/aos/1176346521

Information

Published: June, 1984
First available in Project Euclid: 12 April 2007

zbMATH: 0544.62049
MathSciNet: MR740927
Digital Object Identifier: 10.1214/aos/1176346521

Subjects:
Primary: 62G99
Secondary: 62A15

Rights: Copyright © 1984 Institute of Mathematical Statistics

JOURNAL ARTICLE
7 PAGES


SHARE
Vol.12 • No. 2 • June, 1984
Back to Top