非线性趋势KPSS检验、模型误设与检验流程构建

KPSS Test for Nonlinear Trend,Model Misspecification and Construction of Test Process

利用理论推导和蒙特卡洛模拟方法,研究非线性趋势数据生成模型中KPSS检验统计量、趋势项检验统计量分布规律,并总结出KPSS检验流程。理论研究表明,在原假设和备择假设成立时,相关检验统计量在大样本下都收敛到维纳过程的泛函,且KPSS检验不能有效区分趋势类型,模拟研究也得出类似结论。实证研究显示,通过使用KPSS检验流程,可以精确确定数据生成过程。

Based on the theoretical deduction and Monte Carlo simulation,this paper studies the distribution of KPSS and trend test statistics for data generation process with nonlinear trend,and the KPSS test process is also summarized.The theoretical research shows that these test statistics converge in large samples to the function of Wiener process under the null hypothesis and alternative hypothesis,and that the KPSS test can not effectively distinguish the trend type.Similar conclusions are drawn from simulation results.Empirical research indicates that the data generation process can be accurately determined through the use of the KPSS test procedure.