AN EMPIRICAL BAYES TWO-SIDED TEST PROBLEM FOR CONTINUOUS ONE-PARAMETER EXPONENTIAL FAMILIES

被引：11

作者：

韦来生 ^{[1
]}

机构：

[1] University of Science & Technology of China Hefei

来源：

Systems Science and Mathematical Sciences | 1989年 / 04期

基金：

中国国家自然科学基金;

关键词：

Empirical Bayes; two-sided test; exponential family; asymptotically optimality; convergence rates;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

An empirical Bayes(EB)two-sided test problem about the continuousone-parameter exponential family has been discussed.We construct the EB test decisionrule and prove its asymptotical optimality.Further,we get its convergence ratesO(n~(-(λ(s-2))/(2s+1))under suitable conditions,where 0<λ<2,and s>2 is a given natural number.Finally,some examples about the result of the convergence rates are given.

引用

页码：369 / 384

页数：16