Shrinkage Estimation for the Diagonal Multivariate Exponential Families

TL;DR

This paper develops semi-parametric shrinkage estimators for the mean parameters of diagonal multivariate exponential families, demonstrating their asymptotic properties and superior performance over MLE in simulations.

Contribution

It introduces novel shrinkage estimators for a broad class of multivariate distributions and establishes their asymptotic consistency and improved risk performance.

Findings

Estimators are consistent under certain growth conditions of p and n.

Shrinkage estimators outperform MLE in gamma and Poisson cases in simulations.

Asymptotic convergence rates are derived for various distribution classes.

Abstract

We study shrinkage estimation of the mean parameters of a class of multivariate distributions for which the diagonal entries of the corresponding covariance matrix are certain quadratic functions of the mean parameter. This class of distributions includes the diagonal multivariate natural exponential families. We propose two classes of semi-parametric shrinkage estimators for the mean and construct unbiased estimators of the corresponding risk. We establish the asymptotic consistency and convergence rates for these shrinkage estimators under squared error loss as both $n$, the sample size, and $p$, the dimension, tend to infinity. Next, we specialize these results to the diagonal multivariate natural exponential families, which have been classified as consisting of the normal, Poisson, gamma, multinomial, negative multinomial, and hybrid classes of distributions. We establish the consistency of our estimators in the normal, gamma, and negative multinomial cases subject to the condition that $p n^{-1/3} (\log{n})^{4/3} \to 0$, and in the Poisson and multinomial cases if $p n^{-1/2} \to 0$, as $n,p \to \infty$. Simulation studies are provided to evaluate the performance of our estimators and we illustrate that, in the gamma and Poisson cases, our estimators achieve lower risk than the maximum likelihood estimator, thereby demonstrating the superiority of our estimators over the maximum likelihood estimator.