Arash A. Foroushani | Searcharxiv

arXiv2024

A Note on Improved Multivariate Normal Mean Estimation With Unknown Covariance When p Is Greater Than n

In this paper, we highlight a major error in the proofs of the important results of [D.Chételat and M. T. Wells(2012). Improved Multivariate Normal Mean Estimation with Unknown Covariance when p is Greater than n. The Annals of Statistics, Vol. 40, No.6, 3137--3160]. In particular, the proofs of some of their main results are based on Theorem 2 whose proof needs to be revisited. More precisely, there are some major mistakes in the derivation of this important result. Further, under a very realistic assumption about the rank of the estimator of the variance-covariance matrix, we correct the proof of the quoted result.

math.ST↗

arXiv2024

Improved Gaussian Mean Matrix Estimators In High-Dimensional Data

In this paper, we introduce a class of improved estimators for the mean parameter matrix of a multivariate normal distribution with an unknown variance-covariance matrix. In particular, the main results of [D.Chételat and M. T. Wells(2012). Improved Multivariate Normal Mean Estimation with Unknown Covariance when $p$ is Greater than $n$. The Annals of Statistics, Vol. 40, No.6, 3137--3160] are established in their full generalities and we provide the corrected version of their Theorem 2. Specifically, we generalize the existing results in three ways. First, we consider a parameter matrix estimation problem which enclosed as a special case the one about the vector parameter. Second, we propose a class of James-Stein matrix estimators and, we establish a necessary and a sufficient condition for any member of the proposed class to have a finite risk function. Third, we present the conditions for the proposed class of estimators to dominate the maximum likelihood estimator. On the top of these interesting contributions, the additional novelty consists in the fact that, we extend the methods suitable for the vector parameter case and the derived results hold in the classical case as well as in the context of high and ultra-high dimensional data.

math.ST↗