PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Deviance Information Criteria for missing data models
Gilles Celeux, Florence Forbes, Christian Robert and Mike Titterington
Bayesian analysis 2005.

Abstract

The deviance information criterion (DIC) introduced by Spiegelhalte&al 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.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:1897
Deposited By:Florence Forbes
Deposited On:29 December 2005