Bayesian model comparison: Log scores and DIC

We investigate Bayesian approaches to answering the frequently-arising model-specification question (Q:) Is model Mj better than Mj′? We contrast two Bayesian model-comparison methods–log scores and DIC–on their ability to correctly discriminate between fixed-effects Poisson (FEP) and random-effects Poisson (REP) sampling models.

MoreLess

Year of publication:	2014
Authors:	Krnjajić, Milovan ; Draper, David
Published in:	Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 88.2014, C, p. 9-14
Publisher:	Elsevier
Subject:	Bayesian model discrimination \| Calibration \| Cross-validation log score \| DIC \| Full-sample log score \| Prediction

More details

Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10011039774