Unit root test:: An unconditional maximum likelihood approach

被引:0
|
作者
González-Farías, G
Dickey, DA
机构
[1] ITESM, Dept Matemat, Monterrey, NL, Mexico
[2] N Carolina State Univ, Dept Stat, Raleigh, NC 27695 USA
来源
关键词
time series; nonstationary;
D O I
暂无
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
We investigate a test for unit roots in autoregressive time series based on the maximization of the unconditional likelihood. Models including mean and time trend adjustments are considered. We give percentiles for the resulting tests which are more powerful than the currently popular least squares tests. We show that the limit distributions are unchanged for higher order models so that the tests can be used in models with more than one lag. Both normalized bias tests and studentized tests are considered.
引用
收藏
页码:199 / 221
页数:23
相关论文
共 50 条