On the reliability of Chow-type tests for parameter constancy in multivariate dynamic models

被引：51

作者：

Candelon, B ^{[1
]}

Lütkepohl, H ^{[1
]}

机构：

[1] Humboldt Univ, Inst Stat & Okonometrie, Wirtschaftswissenschaftliche Fak, D-10178 Berlin, Germany

来源：

ECONOMICS LETTERS | 2001年 / 73卷 / 02期

关键词：

bootstrap; vector autoregressive process; vector error correction model; stability tests;

D O I：

10.1016/S0165-1765(01)00478-5

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

The small sample properties of two types of Chow tests are investigated in the context of multiple time series systems. It is found that the tests may have substantially distorted size if the sample size is not large relative to the number of parameters in the model under study. In particular the tests reject far too often in this situation. It is shown that bootstrap versions of the tests have much better properties in this respect. In other words, the bootstrap can be used to size-adjust the tests. (C) 2001 Elsevier Science B.V. All rights reserved.

引用

页码：155 / 160

页数：6