自回归模型偏自相关函数截尾性检验  

Truncation Test of Partial Autocorrelation Function for Autoregressive Model

作　　者：赵志文[1] 杨慧超[1] 彭毳鑫[2] Zhao Zhiwen;Yang Huichao;Peng Cuixin(College of Mathematics, , Jilin Normal University,Siping 川in 136000, China;Public Foreign Languages Department, Jilin Normal University,Siping 川in 136000, China)

机构地区：[1]吉林师范大学数学学院,吉林四平136000 [2]吉林师范大学大学外语部,吉林四平136000

出　　处：《统计与决策》2019年第8期5-8,共4页Statistics & Decision

基　　金：国家自然科学基金资助项目(11571138);国家社会科学基金资助项目(16BTJ020)

摘　　要：文章研究了自回归模型偏自相关函数截尾性检验问题。基于经验似然方法建立了检验统计量,并且在原假设下给出了检验统计量的极限分布。并通过随机模拟将上述方法用于具体观测数据的实证研究,模拟结果表明上述方法具有可行性。This paper studies the truncation test of partial autocorrelation function in autoregressive model. Firstly based on the empirical likelihood method, the paper establishes test statistics, and then gives the limit distribution of test statistics under the null hypothesis. Finally, the paper applies the above method to the empirical study of specific observation data through random simulation, and the results show that the proposed method is feasible.

关 键 词：自回归模型 经验似然 偏自相关函数 最小二乘 

分 类 号：O212[理学—概率论与数理统计]