KSS检验中漂移项与趋势项检验量分布研究  

Research on Distribution for Drift and Trend Statistics Based on KSS Test

作　　者：江海峰[1] 庄健[1] 杨海文[2] 

机构地区：[1]安徽工业大学商学院,安徽马鞍山243032 [2]井冈山大学数理学院,江西吉安343009

出　　处：《安徽工业大学学报（自然科学版）》2015年第1期85-91,共7页Journal of Anhui University of Technology（Natural Science）

基　　金：国家社会科学基金项目(13BJY011)

摘　　要：以数据生成是否含漂移项为依据,采用ADF检验模式分两种情况讨论非线性单位根KSS检验中漂移项、趋势项检验量分布。结果表明:在大样本下二者均收敛到维纳过程的泛函,为非标准分布。为在实证分析中使用这些检验量,通过蒙特卡罗模拟获得有限样本下常用临界值,模拟结果显示:虽然这些临界值随着样本的增加而上升或下降,但呈现稳定态势,且与理论分析结果相符。Based on whether the data generating process contains the drift or not, with ADF test mode, the distributions of the drift and trend statistics composed in nonlinear KSS unit root test were firstly deduced. The theoretic results show that these test statistics converge in distribution to the function of Wiener process, which manifests that these distributions are nonstandard. To apply these statistics to empirical research, the critical values were also obtained for finite samples with Monte Carlo Simulation. Simulation results demonstrate that although these values increase or decrease with the sample size increase, they are stable when the sample approaches to infinity and in accordance with the results of theoretical analysis.

关 键 词：单位根 KSS检验 蒙特卡洛模拟 

分 类 号：F224.0[经济管理—国民经济]