Equivariant minimax dominators of the MLE in the array normal model

DOI10.1016/J.JMVA.2015.01.020zbMATH Open1329.62257arXiv1408.0424OpenAlexW2033217970WikidataQ41282788 ScholiaQ41282788MaRDI QIDQ149115FDOQ149115

David Gerard, Peter D. Hoff, Peter Hoff, David Gerard

Publication date: May 2015

Published in: Journal of Multivariate Analysis (Search for Journal in Brave)

Abstract: Inference about dependencies in a multiway data array can be made using the array normal model, which corresponds to the class of multivariate normal distributions with separable covariance matrices. Maximum likelihood and Bayesian methods for inference in the array normal model have appeared in the literature, but there have not been any results concerning the optimality properties of such estimators. In this article, we obtain results for the array normal model that are analogous to some classical results concerning covariance estimation for the multivariate normal model. We show that under a lower triangular product group, a uniformly minimum risk equivariant estimator (UMREE) can be obtained via a generalized Bayes procedure. Although this UMREE is minimax and dominates the MLE, it can be improved upon via an orthogonally equivariant modification. Numerical comparisons of the risks of these estimators show that the equivariant estimators can have substantially lower risks than the MLE.

Full work available at URL: https://arxiv.org/abs/1408.0424

Recommendations

• Other classes of minimax estimators of variance covariance matrix in multivariate normal distribution
• Improved Minimax Estimators of Normal Convariance and Precision Matrices
• scientific article; zbMATH DE number 758459
• Empirical Bayes minimax estimators of matrix normal means
• Equivariant estimators of the covariance matrix

zbMATH Keywords

covariance estimationBayesian estimationGibbs samplingStein's losstensor data

Mathematics Subject Classification ID

Point estimation (62F10) Bayesian inference (62F15) Estimation in multivariate analysis (62H12) Minimax procedures in statistical decision theory (62C20)

Cites Work

• The mle algorithm for the matrix normal distribution
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Multivariate T-Distributions and Their Applications
• Applied Multiway Data Analysis
• Tensor Decompositions and Applications
• Some matrix-variate distribution theory: Notational considerations and a Bayesian application
• An orthogonally invariant minimax estimator of the covariance matrix of a multivariate normal population
• Best equivariant estimators of a Cholesky decomposition
• The variational form of certain Bayes estimators
• Estimation of a covariance matrix using the reference prior
• A representation of Bayes invariant procedures in terms of Haar measure
• Testing for separability of spatial\,-\,temporal covariance functions
• Separable covariance arrays via the Tucker product, with applications to multivariate relational data
• Array variate random variables with multiway Kronecker delta covariance matrix structure
• Estimation with quadratic loss.
• Invariance, Minimax Sequential Estimation, and Continuous Time Processes
• Title not available (Why is that?)
• Determinant Inequalities via Information Theory
• Title not available (Why is that?)
• Amenability: A survey for statistical applications of hunt-stein and related conditions on groups
• Title not available (Why is that?)
• An asymptotic test for separability of a spatial autoregressive model
• A Multilinear Singular Value Decomposition
• On the Best Rank-1 and Rank-(R₁ ,R₂ ,. . .,R_N) Approximation of Higher-Order Tensors
• Geodesic Convexity and Covariance Estimation
• Title not available (Why is that?)
• Tensor Rank and the Ill-Posedness of the Best Low-Rank Approximation Problem
• The multilinear normal distribution: introduction and some basic properties

Cited In (7)

• Estimation of a multiplicative correlation structure in the large dimensional case
• A note on minque for normal models
• Factor uniqueness of the structural Parafac model
• tensr
• A higher-order LQ decomposition for separable covariance models
• Rational maximum likelihood estimators of Kronecker covariance matrices
• Data-driven optimal shrinkage of singular values under high-dimensional noise with separable covariance structure with application

This page was built for publication: Equivariant minimax dominators of the MLE in the array normal model

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q149115)