学院动态

学术报告信息发布

当前位置: 首页 >> 学术报告信息发布 >> 正文

Asymptotics of high-dimensional time series

发布日期:2024-08-04    作者:     点击:

报告题目:Asymptotics of high-dimensional time series

报告时间:202485上午1000

报告地点:南湖校区老图书馆四楼左侧研究生5-1学习室

主办单位:数学与统计学院

报告人:潘光明

报告人简介:潘光明,新加坡南洋理工大学教授,博士生导师。2002年硕士毕业于安徽大学,2005年博士毕业于中国科学技术大学,之后在新加坡国立大学、荷兰埃因霍温科技大学等做博士后和学术交流工作;2008年以来,在新加坡南洋理工大学工作。研究领域包括高维统计推断、随机矩阵理论、多元统计、应用概率等。至今已在Annals ofStatisticsJournal of American Statistical AssociationJournal of Royal Statistical Society ( B)Annals of ProbabilityAnnals of Applied ProbabilityBernoulliIEEE Transactions on Signal Pro-cessingIEEE Transactions on Information Theory等顶级统计学杂志上发表60余篇学术论文。现为国际统计学会会员(Elected Member of international Statistical Institute),《Random Matrices: Theory and  Applications》杂志编委。

摘要:We consider four structures of high dimensional time series in terms of factor structure and nonstationary

We propose a novel approach to identifying them. The proposed three-step method includes:

(1) the ratio statistic of empirical eigenvalues;

(2) a projected Augmented Dickey-Fuller Test;

(3) a new unit-root test based on the largest empirical eigenvalues.


上一条:Model-free Feature Screening Based on Hellinger Distance for Ultrahigh Dimensional Data

下一条:GCM-DiffHiC: Gaussian convolution based method for differential chromatin interactions detection