Deviation information criteria for missing data models

Celeux, G., Forbes, F., Robert, C.P. and Titterington, D.M. (2006) Deviation information criteria for missing data models. Bayesian Analysis, 1(4), pp. 651-706. (doi:10.1214/06-BA122)

Full text not currently available from Enlighten.

Publisher's URL: http://dx.doi.org/10.1214/06-BA122

Abstract

The deviance information criterion (DIC) introduced by Spiegelhalter et al. (2002) for model assessment and model comparison is directly inspired by linear and generalised linear models, but it is open to different possible variations in the setting of missing data models, depending in particular on whether or not the missing variables are treated as parameters. In this paper, we reassess the criterion for such models and compare different DIC constructions, testing the behaviour of these various extensions in the cases of mixtures of distributions and random effect models.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Titterington, Professor Michael
Authors: Celeux, G., Forbes, F., Robert, C.P., and Titterington, D.M.
Subjects:Q Science > QA Mathematics
College/School:College of Science and Engineering > School of Mathematics and Statistics > Statistics
Journal Name:Bayesian Analysis
ISSN:1931-6690

University Staff: Request a correction | Enlighten Editors: Update this record