Paper Abstract

Flexible Covariance Estimation in Graphical Gaussian Models

Bala Rajaratnam 1, Helene Massam2, Carlos M. Carvalho3

1Stanford University & 2York University & 3University of Chicago

April 2008

To appear in: Annals of Statistics

In this paper, we propose a class of Bayes estimators for the covariance matrix of graphical Gaussian models Markov with respect to a decomposable graph G. Working with the W_{P_G} family we derive closed-form expressions for Bayes estimators under the entropy and squared-error losses. The W_{P_G} family defined by Letac and Massam (2007) includes the classical inverse of the hyper inverse Wishart but has many more shape parameters, thus allowing for flexibility in differentially shrinking various parts of the covariance matrix. Moreover, using this family avoids recourse to MCMC, often infeasible in high-dimensional problems. We illustrate the performance of our estimators through a collection of numerical examples where we explore frequentist risk properties and the efficacy of graphs in the estimation of high-dimensional covariance structures.

PDF


Part of this work was done while B. Rajaratnam was a postdoctoral fellow at SAMSI and H. Massam a Research Fellow in residence at SAMSI and support is gratefully acknowledged. H. Massam was also supported by NSERC Discovery Grant A8946. All three authors gratefully acknowledge support from the American Institute of Mathematics.