Translator Disclaimer
2011 A Metropolis-Hastings based method for sampling from the G-Wishart distribution in Gaussian graphical models
Nicholas Mitsakakis, Hélène Massam, Michael D. Escobar
Electron. J. Statist. 5: 18-30 (2011). DOI: 10.1214/11-EJS594

Abstract

In Gaussian graphical models, the conjugate prior for the precision matrix K is called G-Wishart distribution, WG(δ,D). In this paper we propose a new sampling method for the WG(δ,D) based on the Metropolis Hastings algorithm and we show its validity through a number of numerical experiments. We show that this method can be easily used to estimate the Deviance Information Criterion, providing with a computationally inexpensive approach for model selection.

Citation

Download Citation

Nicholas Mitsakakis. Hélène Massam. Michael D. Escobar. "A Metropolis-Hastings based method for sampling from the G-Wishart distribution in Gaussian graphical models." Electron. J. Statist. 5 18 - 30, 2011. https://doi.org/10.1214/11-EJS594

Information

Published: 2011
First available in Project Euclid: 19 January 2011

zbMATH: 1274.65009
MathSciNet: MR2763796
Digital Object Identifier: 10.1214/11-EJS594

Rights: Copyright © 2011 The Institute of Mathematical Statistics and the Bernoulli Society

JOURNAL ARTICLE
13 PAGES


SHARE
Back to Top