文章基本信息

标题：Unit Root Model Selection
本地全文：下载
作者：Peter C. B. Phillips
期刊名称：JOURNAL OF THE JAPAN STATISTICAL SOCIETY
印刷版ISSN：1882-2754
电子版ISSN：1348-6365
出版年度：2008
卷号：38
期号：1
页码：65-74
DOI：10.14490/jjss.38.65
出版社：JAPAN STATISTICAL SOCIETY
摘要：Some limit properties for information based model selection criteria are given in the context of unit root evaluation and various assumptions about initial conditions. Allowing for a nonparametric short memory component, standard information criteria are shown to be weakly consistent for a unit root provided the penalty coefficient C_n→∞ and C_n/n→ 0 as n→∞ . Strong consistency holds when C_n/ (log log n )³ →∞ under conventional assumptions on initial conditions and under a slightly stronger condition when initial conditions are infinitely distant in the unit root model. The limit distribution of the AIC criterion is obtained.
关键词：AIC;consistency;model selection;nonparametric;unit root