Admissible Bayes equivariant estimation of location vectors for spherically symmetric distributions with unknown scale

DOI10.1214/19-AOS1837MaRDI QIDQ2196207zbMATH OpenFDO

Authors Yuzo Maruyama, William E. Strawderman

Publication date 28 August 2020

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1710.02794, https://projecteuclid.org/euclid.aos/1590480045

zbMATH Keywords

admissibilityBayes equivariancegeneralized BayesStein's phenomenon

Mathematics Subject Classification ID

Admissibility in statistical decision theory (62C15) Minimax procedures in statistical decision theory (62C20) Linear regression; mixed models (62J05) Ridge regression; shrinkage estimators (Lasso) (62J07)

Abstract: This paper investigates estimation of the mean vector under invariant quadratic loss for a spherically symmetric location family with a residual vector with density of the form $f(x,u)=et{a}^{(p+n)/2}f(eta|x-heta{|}^2+|u{|}^2)$, where $eta$ is unknown. We show that the natural estimator $x$ is admissible for $p=1,2$. Also, for $pgeq3$, we find classes of generalized Bayes estimators that are admissible within the class of equivariant estimators of the form $1-xi(x/|u|)x$. In the Gaussian case, a variant of the James--Stein estimator, $[1-(p-2)/(n+2)/|x{|}^2/|u{|}^2+(p-2)/(n+2)+1]x$, which dominates the natural estimator $x$, is also admissible within this class. We also study the related regression model.

Review text

The authors establish the admissibility of certain generalized Bayes estimators within the class of equivariant estimators, of the mean vector for a spherically symmetric distribution with unknown scale under invariants loss. In the Gaussian case, they establish admissibility within the equivariant estimators of a class of generalized Bayes minimax estimators of a particularly simple form. Similar issues in the setting of a general linear regression model with intercept and spherically symmetric error distribution are also investigated. In this setting, the shrinkage factor of equivariant estimators of the regression coefficients depends on the coefficient of determination.

Recommendations

• Generalized Bayes minimax estimators of location vectors for spherically symmetric distributions with residual vector
• Estimation of location parameters for spherically symmetric distributions
• A robust generalized Bayes estimator improving on the James-Stein estimator for spherically symmetric distributions
• Admissibility and minimaxity of generalized Bayes estimators for spherically symmetric family
• Estimation of the mean of a spherically symmetric distribution with constraints on the norm

Cites work

• A new class of generalized Bayes minimax ridge regression estimators
• A robust generalized Bayes estimator improving on the James-Stein estimator for spherically symmetric distributions
• A sharp boundary for SURE-based admissibility for the normal means problem under unknown scale
• A unified approach to improving equivariant estimators
• Admissibility and minimaxity of generalized Bayes estimators for spherically symmetric family
• Admissible Estimators, Recurrent Diffusions, and Insoluble Boundary Value Problems
• All estimates with a given risk, Riccati differential equations and a new proof of a theorem of Brown
• An admissibility proof using an adaptive sequence of smoother proper priors approaching the target improper prior
• An extended class of minimax generalized Bayes estimators of regression coefficients
• Estimation with quadratic loss.
• scientific article; zbMATH DE number 3122730 (Why is no real title available?)
• scientific article; zbMATH DE number 3938231 (Why is no real title available?)
• scientific article; zbMATH DE number 3557007 (Why is no real title available?)
• scientific article; zbMATH DE number 3349081 (Why is no real title available?)
• Improving on equivariant estimators
• On Minimax Statistical Decision Procedures and their Admissibility
• Proper Bayes Minimax Estimators of the Multivariate Normal Mean
• Proper Bayes minimax estimators of the multivariate normal mean vector for the case of common unknown variances
• Robust shrinkage estimators of the location parameter for elliptically symmetric distributions

Cited in

(15)

• An admissibility proof using an adaptive sequence of smoother proper priors approaching the target improper prior
• Bayesian estimation for spherically symmetric distributions
• On discrete priors and sparse minimax optimal predictive densities
• Bayesian predictive density estimation for a chi-squared model using information from a normal observation with unknown mean and variance
• On admissible estimation of a mean vector when the scale is unknown
• Admissibility and minimaxity of generalized Bayes estimators for spherically symmetric family
• Generalized Bayes minimax estimators of location vectors for spherically symmetric distribu\-tions
• Inadmissibility of the usual estimator for the location parameters of spherically symmetric distributions
• Estimation in spherically symmetric regression with random design
• A robust generalized Bayes estimator improving on the James-Stein estimator for spherically symmetric distributions
• Data based loss estimation of the mean of a spherical distribution with a residual vector
• On global-local shrinkage priors for count data
• Bayesian shrinkage estimation for stratified count data
• A class of minimax generalized Bayes estimators and an extended correlation inequality
• Pitman estimation on \({\mathbb{R}}^ k\)

This page was built for publication: Admissible Bayes equivariant estimation of location vectors for spherically symmetric distributions with unknown scale

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2196207)