Abstract
The paper considers estimation of matrix normal means. A class of empirical Bayes estimators is proposed which dominates the maximum likelihood estimator simultaneously for many quadratic losses. Several of these empirical Bayes estimators are compared in terms of their simulated risks, and a concrete recommendation is made about the choice of a particular empirical Bayes estimator.
Original language | English |
---|---|
Pages (from-to) | 306-318 |
Number of pages | 13 |
Journal | Journal of Multivariate Analysis |
Volume | 38 |
Issue number | 2 |
DOIs | |
State | Published - 1 Jan 1991 |
Keywords
- Bayes risks
- Wishart identity
- empirical Bayes
- frequentist risks
- matrix normal means
- minimax