高次趋势单位根检验中高次趋势项系数的t统计量研究  

Study on t Statistics of High Order Trend Term Coefficient in Unit Root Test With High Order Trend

作　　者：左秀霞[1] Zuo Xiuxia(School of Finance and Economics,Jiangsu University,Zhenjiang Jiangsu 212013,China)

机构地区：[1]江苏大学财经学院,江苏镇江212013

出　　处：《统计与决策》2021年第21期29-35,共7页Statistics & Decision

基　　金：全国统计科学研究项目(2020LY109);江苏省教育厅高校哲学社会科学基金一般项目(2020SJA2061)。

摘　　要：文章采用蒙特卡罗仿真得到了小样本和有限样本高次趋势DF单位根检验中趋势项系数的t统计量在常用检验水平下的临界值,并与现有研究的结果进行了比较,在此基础上分析了其临界值在样本量和趋势项阶数变化过程中的变动规律。结果显示:临界值与现有研究非常接近,统计量的小样本和有限样本分布比渐近分布更分散,且其分散的趋势随着样本量的减小更加明显,随着趋势项阶数的增大,统计量的分布更分散,但分散的幅度不断减小。This paper uses Monte Carlo simulation to obtain the critical value of the t-statistic of the trend term coefficient in the high-order trend DF unit root test of small and limited samples under the common test level, and then compares with the results of existing studies, on the basis of which the changing rule of the critical value in the changing process of sample size and trend term order is analyzed. The results are shown as below: The critical value is very close to the existing studies;the small sample and limited sample distribution of statistics are more dispersed than the asymptotic distribution;the trend of dispersion becomes more obvious with the decrease of sample size. As the order of trend term increases, the distribution of statistics becomes more dispersed, but the dispersion degree decreases.

关 键 词：高次趋势 单位根检验 t统计量 蒙特卡罗仿真 

分 类 号：F224.0[经济管理—国民经济]