平稳自回归模型的经验似然检验  

Empirical Likelihood Test for Stationary Short Memory Time Series Models

作　　者：张秀珍 陆智萍[1] 李梦珂 张腾飞[1] 林俊杰 ZHANG Xiuzhen;LU Zhiping;LI Mengke;ZHANG Tengfei;LIN Junjie(School of Statistics,East China Normal University,Shanghai,200241,China;School of Mathematics and Statistics,Shanxi Datong University,Datong,037009,China)

机构地区：[1]华东师范大学统计学院,上海200241 [2]山西大同大学数学与统计学院,大同037009

出　　处：《应用概率统计》2021年第4期377-389,共13页Chinese Journal of Applied Probability and Statistics

基　　金：supported by the Natural Science Foundation of Shanghai(Grant No.17ZR1409000);the National Natural Science Foundation of China(Grant No.11971171);the 111 Project(Grant No.B14019);the Project of National Social Science Fund of China(Grant No.15BTJ027).

摘　　要：这篇文章中,我们对平稳短记忆时间序列模型中的参数假设检验运用经验似然方法,在实际中,我们可能不仅关心所有参数的显著性而且更关心模型中的某一部分参数是否存在,因而我们除了建立检验所有参数的统计量,还建立了检验部分参数显著与否的统计量,这些统计量被证实都渐近服从卡方分布,另外,我们的模拟研究了检验的势函数并证实了提出的检验程序的有效性.In this paper,we propose empirical likelihood method for parameter hypothesis test in short memory time series models.In practice,we may pay attention to not only the significance of all the parameters,but also the significance of some parameter in the models.So we construct different test statistics in these two situations,which are both shown to follow chi-square distributions asymptotically.In addition,our simulations investigate the power function for testing the concerned parameters and verify the validity of the proposed testing procedure.

关 键 词：经验似然 调整经验似然 平稳自回归滑动平均模型 

分 类 号：O212.7[理学—概率论与数理统计]