Generalized Bayes minimax estimators of the mean of multivariate normal distribution with unknown variance

被引:12
|
作者
Wells, Martin T. [1 ]
Zhou, Gongfu [2 ]
机构
[1] Cornell Univ, Dept Stat Sci, Ithaca, NY 14853 USA
[2] Yale Univ, Dept Epidemiol & Publ Hlth, New Haven, CT 06520 USA
关键词
Generalized Bayes estimate; Integration by parts; Minimax estimate; Multivariate normal mean; Invariant loss; Unknown variance; Weakly differentiable function;
D O I
10.1016/j.jmva.2008.02.016
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
We construct a broad class of generalized Bayes minimax estimators of the mean of a multivariate normal distribution with covariance equal to sigma I-2(p), with sigma(2) unknown, and under the invariant loss parallel to delta(X) - theta parallel to(2)/sigma(2). Examples that illustrate the theory are given. Most notably it is shown that a hierarchical version of the multivariate Student-t prior yields a Bayes minimax estimate. (C) 2008 Elsevier Inc. All rights reserved.
引用
收藏
页码:2208 / 2220
页数:13
相关论文
共 50 条