Bayes minimax estimation of the mean matrix of matrix-variate normal distribution under balanced loss function

被引：11

作者：

Zinodiny, S. ^{[1
]}

Rezaei, S. ^{[1
]}

Nadarajah, S. ^{[2
]}

机构：

[1] Amirkabir Univ Technol, Tehran, Iran

[2] Univ Manchester, Manchester, Lancs, England

来源：

STATISTICS & PROBABILITY LETTERS | 2017年 / 125卷

关键词：

Balanced loss function; Bayes estimation; Matrix-variate normal distribution; Mean matrix; Minimax estimation; CORRELATION INEQUALITIES; VECTOR;

D O I：

10.1016/j.spl.2017.02.003

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：

This note considers the problem of simultaneous estimation of matrix-variate normal mean matrix using a balanced loss function when common variance sigma(2) is unknown. We first find a class of minimax estimators for this problem and show that the maximum likelihood estimator is inadmissible. We obtain a large class of (proper and generalized) Bayes minimax estimators for the mean matrix. (C) 2017 Elsevier B.V. All rights reserved.

引用

页码：110 / 120

页数：11

共 12 条

[1]

[Anonymous], 1973, P PRAG S AS

[2] MINIMAX ESTIMATORS IN THE NORMAL MANOVA MODEL [J].