Speaker: Dr. Yuli Liang (梁宇莉博士)

Time: 12:10-13:10, 22 December 2022 (Thursday) (Beijing time)

Tencent Meeting ID: 237-923-120

Abstract

In this paper the Rao score and likelihood ratio tests for hypothesis related to the covariance structure of doubly multivariate models are studied. For the hypothesis related to hierarchical dependence such that the intercalss and intraclass correlations belong to the space of (commutative) quadratic structures the Rao score and likelihood ratio test statistics are derived as well as the exact distributions of the likelihood ratio test is determined. Simulation studies show the advantage of the Rao score test over the likelihood ratio test in the context of convergence to the limiting chi-square distribution, while both of proposed tests are competitive from the point of view of their power. Presented results are applied to real data example.

About Dr. Liang

梁宇莉博士为瑞典林奈大学经济学院经济与统计系助理教授，硕士生导师，曾任瑞典厄勒布鲁大学商学院统计系教职和瑞典国家统计局方法论部门资深统计师(senior methodologist)，于乌普萨拉大学获统计学硕士学位，后于斯德哥尔摩大学获统计学博士学位。主要研究兴趣为含协方差结构的多元模型和高维数据分析，已在包括Biometrical Journal, Statistical Paper在内的国际SCI期刊上发表论文数篇。