A service provided by the WU Library and the WU IT-Services

Model Likelihoods and Bayes Factors for Switching and Mixture Models

Frühwirth-Schnatter, Sylvia (2002) Model Likelihoods and Bayes Factors for Switching and Mixture Models. Report Series SFB "Adaptive Information Systems and Modelling in Economics and Management Science", 70. SFB Adaptive Information Systems and Modelling in Economics and Management Science, WU Vienna University of Economics and Business, Vienna.

[img]
Preview
PDF
Download (3425Kb) | Preview

Abstract

In the present paper we discuss the problem of estimating model likelihoods from the MCMC output for a general mixture and switching model. Estimation is based on the method of bridge sampling (Meng and Wong, 1996), where the MCMC sample is combined with an iid sample from an importance density. The importance density is constructed in an unsupervised manner from the MCMC output using a mixture of complete data posteriors. Whereas the importance sampling estimator as well as the reciprocal importance sampling estimator are sensitive to the tail behaviour of the importance density, we demonstrate that the bridge sampling estimator is far more robust in this concern. Our case studies range from computing marginal likelihoods for a mixture of multivariate normal distributions, testing for the inhomogeneity of a discrete time Poisson process, to testing for the presence of Markov switching and order selection in the MSAR model. (author's abstract)

Item Type: Paper
Keywords: Bayesian model choice / bridge sampling / marginal likelihoods / Markov switching models switching models / mixture models
Divisions: Departments > Informationsverarbeitung u Prozessmanag. > Produktionsmanagement > Taudes
Departments > Finance, Accounting and Statistics > Statistics and Mathematics
Departments > Marketing > Service Marketing und Tourismus
Departments > Informationsverarbeitung u Prozessmanag. > Informationswirtschaft
Depositing User: Repository Administrator
Date Deposited: 20 Jan 2003 14:32
Last Modified: 05 Oct 2014 08:35
URI: http://epub.wu.ac.at/id/eprint/474

Actions

View Item