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
收藏
页码：369 / 384
页数：16
相关论文
共 50 条
12345