高维周期向量自回归模型的精度矩阵的假设检验  

Hypothesis testing for the precision matrix of high-dimensional periodic vector autoregressive model

作　　者：邹进 ZOU Jin(School of Mathematical Sciences,Shanghai Jiao Tong University,Shanghai 200240,China)

机构地区：[1]上海交通大学数学科学学院,上海200240

出　　处：《华东师范大学学报（自然科学版）》2023年第2期48-59,共12页Journal of East China Normal University(Natural Science)

基　　金：国家自然科学基金(11531001)。

摘　　要：由周期性向量自回归模型生成的精度矩阵(逆协方差矩阵)是一个块状三对角矩阵.在此精度矩阵的基础上,提出了一种新的块状迹函数,用于检验两个精度矩阵的块状迹相等,并研究了在零假设下的渐近行为.数值实验表明,这种块状迹函数检验方法与常用的检验方法相比,具有简洁易算和功效优良的特点.The precision(inverse covariance) matrix generated by the periodic vector autoregressive model is a sparse block tridiagonal matrix. Based on this precision matrix, a new block trace function is proposed for testing the equality of block traces of two precision matrices, the asymptotic behavior under the null hypothesis is investigated. Numerical experiments show that the proposed testing procedure has both appropriate size and good power.

关 键 词：假设检验 周期性向量自回归模型 精度矩阵 块状三对角矩阵 

分 类 号：O212.1[理学—概率论与数理统计]