A NOTE ON THE UNIFICATION OF THE AKAIKE INFORMATION CRITERION

Authors
Citation
Pd. Shi et Cl. Tsai, A NOTE ON THE UNIFICATION OF THE AKAIKE INFORMATION CRITERION, Journal of the Royal Statistical Society. Series B: Methodological, 60, 1998, pp. 551-558
Citations number
13
Categorie Soggetti
Statistic & Probability","Statistic & Probability
Journal title
Journal of the Royal Statistical Society. Series B: Methodological
ISSN journal
13697412 → ACNP
Volume
60
Year of publication
1998
Part
3
Pages
551 - 558
Database
ISI
SICI code
1369-7412(1998)60:<551:ANOTUO>2.0.ZU;2-A
Abstract
To measure the distance between a robust function evaluated under the true regression model and under a fitted model, we propose generalized Kullback-Leibler information. Using this generalization we have devel oped three robust model selection criteria, AICR, AICCR* and AICCR, t hat allow the selection of candidate models that not only fit the majo rity of the data but also take into account non-normally distributed e rrors. The AICR and AICCR criteria can unify most existing Akaike inf ormation criteria; three examples of such unification are given. Simul ation studies are presented to illustrate the relative performance of each criterion.