The influence of heteroskedastic variances on cointegration tests: A comparison using Monte Carlo simulations

被引：3
|
作者：
Maki, Daiki [1 ]
机构：
[1] Ryukoku Univ, Fac Econ, Fushimi Ku, Kyoto 6128577, Japan
来源：
COMPUTATIONAL STATISTICS | 2013年 / 28卷 / 01期
关键词：
Cointegration; Threshold model; Structural breaks; Heteroskedastic variance; Empirical size; STRUCTURAL BREAKS; ERROR-CORRECTION; UNIT ROOTS; MODELS; RATES;
D O I：
10.1007/s00180-011-0293-x
中图分类号：
O21 [概率论与数理统计]; C8 [统计学];
学科分类号：
020208 ; 070103 ; 0714 ;
摘要：
This paper investigates the influence of heteroskedastic variances on cointegration tests. The Monte Carlo simulation results show that cointegration tests allowing for threshold adjustments or structural breaks overreject the null hypothesis of no cointegration in the presence of GARCH errors and variance breaks. In particular, multivariate GARCH and bivariate variance breaks cause severe size distortions in such cointegration tests. On the other hand, a variance ratio cointegration test yields reasonable empirical sizes under most cases of heteroskedastic variances, as compared to other tests including standard cointegration tests.
引用
收藏
页码：179 / 198
页数：20
相关论文
共 50 条
12345