The performance of covariance selection methods that consider decomposable models only.

Show simple item record Fitch, Anne en Jones, Mary Beatrix en Massam, H en 2018-10-10T00:24:24Z en 2014 en
dc.identifier.citation Bayesian Analysis, 2014, 9 (3), pp. 659 - 684 en
dc.identifier.issn 1931-6690 en
dc.identifier.uri en
dc.description.abstract We consider the behavior of Bayesian procedures that perform model selection for decomposable Gaussian graphical models when the true model is in fact non-decomposable. We examine the asymptotic behavior of the posterior when models are misspecified in this way, and find that the posterior will converge to graphical structures that are minimal triangulations of the true structure. The marginal log likelihood ratio comparing different minimal triangulations is stochastically bounded, and appears to remain data dependent regardless of the sample size. The covariance matrices corresponding to the different minimal triangulations are essentially equivalent, so model averaging is of minimal benefit. Using simulated data sets and a particular high performing Bayesian method for fitting decomposable models, feature inclusion stochastic search, we illustrate that these predictions are borne out in practice. Finally, a comparison is made to penalized likelihood methods for graphical models, which make no decomposability restriction. Despite its inability to fit the true model, feature inclusion stochastic search produces models that are competitive or superior to the penalized likelihood methods, especially at higher dimensions. en
dc.publisher International Society for Bayesian Analysis en
dc.relation.ispartofseries Bayesian Analysis en
dc.rights Items in ResearchSpace are protected by copyright, with all rights reserved, unless otherwise indicated. Previously published items are made available in accordance with the copyright policy of the publisher. en
dc.rights.uri en
dc.rights.uri en
dc.title The performance of covariance selection methods that consider decomposable models only. en
dc.type Journal Article en
dc.identifier.doi 10.1214/14-BA874 en
pubs.issue 3 en
pubs.begin-page 659 en
pubs.volume 9 en
dc.rights.holder Copyright: International Society for Bayesian Analysis en
pubs.end-page 684 en
dc.rights.accessrights en
pubs.subtype Article en
pubs.elements-id 459249 en Science en Statistics en
pubs.number 3 en
pubs.record-created-at-source-date 2018-01-25 en

Files in this item

Find Full text

This item appears in the following Collection(s)

Show simple item record


Search ResearchSpace