The Akaike information criterion, AIC, is widely used for model selection. Using the AIC as the estimator of asymptotic unbias for the second term Kullbake-Leibler risk considers the divergence between the true model and offered models. However, it is an inconsistent estimator. A proposed approach the problem is the use of A'IC, a consistently offered information criterion. Model selection of classic and linear models are considered by a Monte Carlo simulation.
"The Information Criterion,"
Journal of Modern Applied Statistical Methods:
2, Article 25.
Available at: http://digitalcommons.wayne.edu/jmasm/vol13/iss2/25