基于AR(1)的多个结构突变点的面板单位根检验  

Testing for unit roots in panels allowing for multiple structural breaks based on AR

作　　者：徐悦悦 刘利敏[1] Xu Yueyue;Liu Limin(College of Mathematics and Information Science,Henan Normal University,Xinxiang 453007,China)

机构地区：[1]河南师范大学数学与信息科学学院,河南新乡453007

出　　处：《河南师范大学学报（自然科学版）》2018年第3期13-18,共6页Journal of Henan Normal University(Natural Science Edition)

基　　金：国家自然科学基金(71203056);河南师范大学研究生科研创新项目(YL201603);河南师范大学博士科研启动项目(QD14153)

摘　　要：讨论了在AR(1)面板数据模型中,其个体效应上存在多个结构突变点的单位根检验问题.首先通过构造虚拟变量建立模型,假设模型中误差项为序列相关,得到模型的单位根检验统计量;然后在时间维度T有限横截面维度N无穷时得到统计量的渐近分布;最后利用蒙特卡洛模拟验证检验结果并进行实证分析,对中原经济区的宏观经济变量GDP进行单位根检验,结果表明考虑两个结构突变点后的GDP数据是平稳的.In this paper,it discusses the unit root tests of panel data which allow for multiple structural breaks in the individual effects of the AR(1)panel data model.Firstly,the model is established by constructing virtual variables with serial correlation in error terms,so that we could get statistics of the unit root.Then,the limiting distribution of test statistics could be obtained when the time-dimension of the panel T is limited and the cross-section N is infinite.Lastly,the result of testing is verified by Monte Carlo experiments with empirical analysis.The testing result to macroeconomic variables GDP indicates that the data is stationary under the consideration of multiple structural breaks.

关 键 词：面板数据 单位根 结构突变 检验统计量 

分 类 号：O211[理学—概率论与数理统计]