A0234
Title: AIC for many-regressor heteroskedastic regressions
Authors: Stanislav Anatolyev - CERGE-EI and New Economic School (Czech Republic) [presenting]
Abstract: The original and corrected Akaike information criteria (AIC) have been routinely used for model selection for ages. The penalty terms in these criteria are tied to the classical normal linear regression, characterized by conditional homoskedasticity and a small number of regressors relative to the sample size. We derive, from the same principles, a general version that takes account of conditional heteroskedasticity and regressor numerosity. The new AICm penalty takes the form of a ratio of certain weighted average error variances and can be operationalized via unbiased estimation of individual variances. The feasible AICm criterion still minimizes the expected Kullback-Leibler divergence up to an asymptotically negligible term that does not relate to regressor numerosity. In simulations, the feasible AICm does select models that deliver systematically better out-of-sample predictions than the classical criteria.
