On extension of some identities for the bias and risk functions in elliptically contoured distributions

JOURNAL OF MULTIVARIATE ANALYSIS

卷:122

Article

Nkurunziza, Severien¹  Chen, Fuqi¹ 

[1] Univ Windsor, Dept Math & Stat, Windsor, ON N9B 3P4, Canada

关键词: Bias function;    Elliptically contoured distribution;    Kronecker-product;    Matrix estimation;    Risk function;    Stein rules;   

DOI  :  10.1016/j.jmva.2013.07.005

来源: Elsevier

【 摘 要 】

In this paper, we are interested in an estimation problem concerning the mean parameter of a random matrix whose distribution is elliptically contoured. We derive two general formulas for the bias and risk functions of a class of multidimensional shrinkage-type estimators. As a by product, we generalize some recent identities established in Gaussian sample cases for which the shrinking random part is a single Kronecker-product. Here, the variance-covariance matrix of the shrinking random part is the sum of two Kronecker-products. (C) 2013 Elsevier Inc. All rights reserved.

【 授权许可】

Free