Open Access
Translator Disclaimer
March, 1991 Asymptotic Optimality of Bayes Compound Estimators in Compact Exponential Families
Somnath Datta
Ann. Statist. 19(1): 354-365 (March, 1991). DOI: 10.1214/aos/1176347987

Abstract

The problem of finding admissible, asymptotically optimal compound rules is pursued in the infinite state case. The components involve the estimation of an arbitrary continuous transform of the natural parameter of a real exponential family with compact parameter space. We show that all Bayes estimators are admissible. Our main result is that any Bayes compound estimator versus a mixture of i.i.d. priors on the compound parameter is asymptotically optimal if the mixing hyperprior has full support. The asymptotic optimality results are generalized to weighted squared error loss with continuous weight function and applications to some nonexponential situations are also considered. Several examples of such hyperpriors are given and for some of them practically useful forms of the corresponding Bayes estimators are obtained.

Citation

Download Citation

Somnath Datta. "Asymptotic Optimality of Bayes Compound Estimators in Compact Exponential Families." Ann. Statist. 19 (1) 354 - 365, March, 1991. https://doi.org/10.1214/aos/1176347987

Information

Published: March, 1991
First available in Project Euclid: 12 April 2007

zbMATH: 0741.62004
MathSciNet: MR1091856
Digital Object Identifier: 10.1214/aos/1176347987

Subjects:
Primary: 62C25
Secondary: 62C15

Keywords: asymptotic optimality , Bayes compound estimators , consistency , exponential families , prior

Rights: Copyright © 1991 Institute of Mathematical Statistics

JOURNAL ARTICLE
12 PAGES


SHARE
Vol.19 • No. 1 • March, 1991
Back to Top