# zbMATH — the first resource for mathematics

Equivariant estimators of the covariance matrix. (English) Zbl 0702.62048
Summary: Given a Wishart matrix S $$[S\sim W_ p(n,\Sigma)]$$ and an independent multinormal vector X $$[X\sim N_ p(\mu,\Sigma)]$$, equivariant estimators of $$\Sigma$$ are proposed. These estimators dominate the best multiple of S and the Stein-type truncated estimators.

##### MSC:
 62H12 Estimation in multivariate analysis 62A01 Foundations and philosophical topics in statistics 62C15 Admissibility in statistical decision theory
Full Text:
##### References:
 [1] Brewster, Improving on equivariant estimators, Ann. Statist. 2 pp 21– (1974) · Zbl 0275.62006 [2] Dey, Estimation of covariance matrix under Stein’s loss, Ann. Statist. 13 pp 1581– (1985) [3] Haff, Empirical Bayes estimation of the multivariate normal covariance matrix, Ann. Statist. 8 pp 586– (1980) · Zbl 0441.62045 [4] James, Estimation with quadratic loss, Proc. Fourth Berkeley Symp. Statist. Probab. 1 pp 361– (1961) · Zbl 1281.62026 [5] Kubokawa, Improved estimation of a covariance matrix under quadratic loss, Statist. Probab. Lett. 8 pp 69– (1989) · Zbl 0667.62040 [6] Olkin, Statistical Decision Theory and Related Topics pp 2– (1977) [7] Sinha, Inadmissibility of the best equivariant estimator of the variance-covariance matrix and the generalized variance under entropy loss, Statist. Decisions 5 pp 201– (1987) · Zbl 0634.62050 [8] Stein, Inadmissibility of the usual estimator of the variance of a normal distribution with unknown mean, Ann. Inst. Statist. Math. 16 pp 155– (1964) · Zbl 0144.41405
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.