Home > Research > Publications & Outputs > Bayesian Inference For Nondecomposable Graphica...
View graph of relations

Bayesian Inference For Nondecomposable Graphical Gaussian Models.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published
  • Petros; Dellaportas
  • Paolo; Giudici
  • Gareth Roberts
Close
<mark>Journal publication date</mark>2003
<mark>Journal</mark>Sankhya - Series A
Issue number1
Volume65
Number of pages13
Pages (from-to)43-55
Publication StatusPublished
<mark>Original language</mark>English

Abstract

In this paper we propose a method to calculate the posterior probability of a nondecomposable graphical Gaussian model. Our proposal is based on a new device to sample from Wishart distributions, conditional on the graphical constraints. As a result, our methodology allows Bayesian model selection within the {\em whole} class of graphical Gaussian models, including nondecomposable ones.