Model weights and the foundations of multimodel inference

By:  and 



Statistical thinking in wildlife biology and ecology has been profoundly influenced by the introduction of AIC (Akaike?s information criterion) as a tool for model selection and as a basis for model averaging. In this paper, we advocate the Bayesian paradigm as a broader framework for multimodel inference, one in which model averaging and model selection are naturally linked, and in which the performance of AIC-based tools is naturally evaluated. Prior model weights implicitly associated with the use of AIC are seen to highly favor complex models: in some cases, all but the most highly parameterized models in the model set are virtually ignored a priori. We suggest the usefulness of the weighted BIC (Bayesian information criterion) as a computationally simple alternative to AIC, based on explicit selection of prior model probabilities rather than acceptance of default priors associated with AIC. We note, however, that both procedures are only approximate to the use of exact Bayes factors. We discuss and illustrate technical difficulties associated with Bayes factors, and suggest approaches to avoiding these difficulties in the context of model selection for a logistic regression. Our example highlights the predisposition of AIC weighting to favor complex models and suggests a need for caution in using the BIC for computing approximate posterior model weights.

Additional publication details

Publication type Article
Publication Subtype Journal Article
Title Model weights and the foundations of multimodel inference
Series title Ecology
Volume 87
Issue 10
Year Published 2006
Language English
Contributing office(s) Patuxent Wildlife Research Center
Description 2626-2635
Larger Work Type Article
Larger Work Subtype Journal Article
Larger Work Title Ecology
First page 2626
Last page 2635
Google Analytic Metrics Metrics page
Additional metadata about this publication, not found in other parts of the page is in this table