讲座人：  李兆媛 副教授，The Chinese University of Hong Kong, Shenzhen (CUHKSZ)

讲座题目：Asymptotic power of the sphericity test under divergent spiked population model

讲座时间：2020/12/03，星期四，上午 9:00-11:00

讲座地点：兴庆校区数学楼2-3会议室（线上线下结合）

讲座简介：

This talk studies the asymptotic power for the sphericity test in a large fixed effect panel data model proposed by Baltagi et al. (2011) and generalized by Li and Yao (2020), the residual-based John's test. This is done under the alternative hypothesis of a general covariance model with divergent spiked eigenvalues, while the other eigenvalues are bounded but otherwise arbitrary. Meanwhile, the number of spikes can keep fixed or diverge as the population dimensions increases. To derive the limiting distribution of the residual-based John's test under the alternative, we first develop the central limit theorem (CLT) for a series of spectral statistics (SS) of the sample covariance matrix under the divergent spiked population model. The general joint CLT of SS is established when the spikes diverge to infinity at the rate of provided a finite forth-moment. Moreover, the joint limiting normal distribution of linear and quadratic polynomial functions is established when the spikes diverge to infinity at the rate of provided finite higher-order moment. These CLT results can be of independent interest. Our results show that the residual-based John's test is consistent under divergent spiked covariance alternative.

讲座人简介：

Dr. Zhaoyuan Li is an Assistant Professor of Statistics at the School of Data Science of The Chinese University of Hong Kong, Shenzhen (CUHKSZ). Prior to that, she has been a post-doctoral fellow in finance at University of Hong Kong and a part-time lecturer at HKU’s Faculty of Business and Economics. Dr. Li’s Primary research interests focus on high-dimensional statistics, random matrix theory and interdisciplinary research. Her research has been published in statistics and interdisciplinary journals, including JRSSB and Nucleic Acids Research (top journal in biochemistry). Dr. Li earned a Bachelor from Xi’an Jiaotong University in 2010, Master in Statistics from Renmin University of China in2012 and Ph.D. in Statistics from University of Hong Kong in 2016.

姜丹丹 邀请您参加腾讯会议

会议主题：李兆媛-统计论坛报告

会议时间：2020/12/3 09:00-11:00

点击链接入会，或添加至会议列表：

https://meeting.tencent.com/s/RcecPrPnY0Pg

会议 ID：835 390 364

手机一键拨号入会

+8675536550000,,835390364# (中国大陆)

+85230018898,,,2,835390364# (中国香港)

根据您的位置拨号

+8675536550000 (中国大陆)

+85230018898 (中国香港)