摘要
本文研究了不同情形下单位根的Wald检验。首先从理论上推导了各种Wald检验统计量的极限分布;然后,运用蒙特卡罗试验,模拟了有限样本容量常用检验水平下的临界值,拟合了临界值关于样本容量的响应面函数,给出了检验统计量的分位数表,并总结了用于单位根检验的Wald统计量有限样本容量下的统计特性。
We analyse the properties of the Wald test statistics for unit root test in different situations in this paper. We verify the limit distribution of the test statistics, and simulate the critical values of the test statistics in finite sample size via Monte Carlo simulations, where the significant level is in common used. Furthermore, the author fits the response surface function of critical value about the sample size. On the basis of the response surface functions, the empirical critical values at different percentages in different sample sizes are tabled. Finally we summarize the Wald statistical properties in finite sample size.
出处
《数量经济技术经济研究》
CSSCI
北大核心
2009年第7期146-158,共13页
Journal of Quantitative & Technological Economics
