Testing for Stationarity in Heterogeneous Panels with Serially Correlated Errors
Testing for Stationarity in Heterogeneous Panels with Serially Correlated Errors
复制标题
具有序列相关误差的异质面板中的平稳性测试
DOI：
--
复制
发表时间：
1999
期刊：
影响因子：
--
通讯作者：
Andy Snell
中科院分区：
文献类型：
--
作者：
Y. Shin;Andy Snell
本文提出了在横截面单元之间存在异质性和时间段之间存在序列相关性的情况下，针对单位根替代的零平稳性进行基于面板的检验。通过联合渐近方法（而不是序贯渐近方法）表明，所提出的检验统计量在大 N（组数）和有限 T（时间段数）的零值下以标准正态分布，附加条件 N/T -> 0。还表明，在具有单位根的各个过程的分数不为零的备择假设下，检验是一致的。蒙特卡罗结果证实了所提出的测试的有效性，并清楚地表明基于面板的测试的功效大大高于基于单一时间序列的测试的功效。
This paper proposes panel-based tests for the null stationary against the alternative of unit roots in the presence of both heterogeneity across cross-section units and serial correlation across time periods. It is shown by the joint asymptotic approach (rather than the sequential asymptotic approach) that the proposed test statistic is distributed as standard normal under the null for large N (number of groups) and finite T (number of time periods) with the additional condition N/T -> 0. It is also shown that the test is consistent under the alternative hypothesis that the fraction of the individual processes that have unit root is non-zero. Monte Carlo results confirm that validity of the proposed test, and clearly indicate that the power of the panel-based test is substantially higher than that of the single time series-based test.