The relative performance of AIC, AICC and BIC in the presence of unobserved heterogeneity

作者: Mark J. Brewer , Adam Butler , Susan L. Cooksley

DOI: 10.1111/2041-210X.12541

关键词: Model selectionStepwise regressionGeneralized linear mixed modelInformation CriteriaAkaike information criterionDeviance information criterionBayesian information criterionStatisticsEconometricsComputer sciencePopulation

摘要: Summary Model selection is difficult. Even in the apparently straightforward case of choosing between standard linear regression models, there does not yet appear to be consensus statistical ecology literature as right approach. We review recent works on model and subsequently focus one aspect particular: use Akaike Information Criterion (AIC) or its small-sample equivalent, AICC. We create a novel framework for simulation studies this study from simulated data sets with range properties, which differ terms degree unobserved heterogeneity. results suggest an approach based ideas information criteria but requiring simulation. We find that relative predictive performance by different heavily dependent heterogeneity sets. When small, AIC AICC are likely perform well, if large, Bayesian (BIC) will often better, due stronger penalty afforded. Our conclusion choice criterion (or more broadly, strength likelihood penalty) should ideally upon hypothesized estimated previous data) properties population given set could have arisen. Relying single form unlikely universally successful.

参考文章(27)
MARK J. WHITTINGHAM, PHILIP A. STEPHENS, RICHARD B. BRADBURY, ROBERT P. FRECKLETON, Why do we still use stepwise modelling in ecology and behaviour Journal of Animal Ecology. ,vol. 75, pp. 1182- 1189 ,(2006) , 10.1111/J.1365-2656.2006.01141.X
Ken Aho, DeWayne Derryberry, Teri Peterson, Model selection for ecologists: the worldviews of AIC and BIC Ecology. ,vol. 95, pp. 631- 636 ,(2014) , 10.1890/13-1452.1
Brian S. Cade, Model averaging and muddled multimodel inferences Ecology. ,vol. 96, pp. 2370- 2382 ,(2015) , 10.1890/14-1639.1
S. T. Buckland, K. P. Burnham, N. H. Augustin, Model selection: An integral part of inference Biometrics. ,vol. 53, pp. 603- 618 ,(1997) , 10.2307/2533961
David A. Freedman, David A. Freedman, A Note on Screening Regression Equations The American Statistician. ,vol. 37, pp. 152- 155 ,(1983) , 10.1080/00031305.1983.10482729
Paul A. Murtaugh, In defense of P values. Ecology. ,vol. 95, pp. 611- 617 ,(2014) , 10.1890/13-0590.1
M. B. Hooten, N. T. Hobbs, A guide to Bayesian model selection for ecologists Ecological Monographs. ,vol. 85, pp. 3- 28 ,(2015) , 10.1890/14-0661.1
Sumio Watanabe, Equations of states in singular statistical estimation Neural Networks. ,vol. 23, pp. 20- 34 ,(2010) , 10.1016/J.NEUNET.2009.08.002
Hirotogu Akaike, Information Theory and an Extension of the Maximum Likelihood Principle international symposium on information theory. ,vol. 1, pp. 610- 624 ,(1973) , 10.1007/978-1-4612-1694-0_15
RITEI SHIBATA, An optimal selection of regression variables Biometrika. ,vol. 68, pp. 45- 54 ,(1981) , 10.1093/BIOMET/68.1.45