A CORRECTED AKAIKE INFORMATION CRITERION FOR VECTOR AUTOREGRESSIVE MODEL SELECTION

作者：Clifford M. Hurvich, Chih‐Ling Tsai · 发表于：Journal of Time Series Analysis · 年份：1993 · DOI：10.1111/j.1467-9892.1993.tb00144.x · 被引用次数：411 · 研究领域：Statistical Methods and Inference、Bayesian Methods and Mixture Models、Statistical Methods and Bayesian Inference

Abstract. We develop a small‐sample criterion (AIC C ) for the selection of the order of vector autoregressive models. AIC C is an approximately unbiased estimator of the expected Kullback‐Leibler information. Furthermore, AIC C provides better model order choices than the Akaike information criterion in small samples.