Bayesian simultaneous estimation for means in k-sample problems

JOURNAL OF MULTIVARIATE ANALYSIS

卷:169

Article

Imai, Ryo¹  Kubokawa, Tatsuya²  Ghosh, Malay³ 

[1] Univ Tokyo, Grad Sch Econ, Bunkyo Ku, 7-3-1 Hongo, Tokyo 1130033, Japan

[2] Univ Tokyo, Fac Econ, Bunkyo Ku, 7-3-1 Hongo, Tokyo 1130033, Japan

[3] Univ Florida, Dept Stat, 102 Griffin Floyd Hall, Gainesville, FL 32611 USA

关键词: Bayes estimator;    Empirical Bayes;    k-sample problem;    Minimaxity;    Quadratic loss;    Shrinkage estimator;   

DOI  :  10.1016/j.jmva.2018.08.013

来源: Elsevier

【 摘 要 】

This paper is concerned with the simultaneous estimation of k population means when one suspects that the k means are nearly equal. As an alternative to the preliminary test estimator based on the test statistics for testing hypothesis of equal means, we derive Bayesian and minimax estimators which shrink individual sample means toward a pooled mean estimator given under the hypothesis. It is shown that both the preliminary test estimator and the Bayesian minimax shrinkage estimators are further improved by shrinking the pooled mean estimator. The performance of the proposed shrinkage estimators is investigated by simulation. (C) 2018 Elsevier Inc. All rights reserved.

【 授权许可】

Free