A monte carlo study on the interaction between model selection and testing nonnormality in autoregressive models

Abstract

We investigate the interaction between model selection procedure and testing nonnormality in autoregressive processes when the sample size is small, we utilize residual skewness, kurtosis and an omnibus statistic as test statistics and AIC, SC and HQ as model selection criteria. The result of a Monte Carlo simulation with some AR(3) models shows that the performance of the statistics from the selected model is as well as those from the true mode 1