主题:Linear hypothesis testing for high dimensional data via wild bootstrapping
主讲人:户文娟 首都经济贸易大学
主持人:王国长 88858cc永利官网
时间:2024年11月10日(周日)上午10:40-11:40
地点:88858cc永利官网石牌校区88858cc永利官网大楼(中惠楼)102室
摘要
In this article, we propose a new nonparametric test for linear hypothesis on regression parameter in linear models with high dimensional explanatory variable, which is a fundamental important problem in the statistical theory and applications. We systematically study the theoretical properties under both the null hypothesis and a local alternative hypothesis, which is the sum of a normal distribution and a mixed chi-square distribution. We conduct a wild bootstrap simulation method based on U centering that could improve the accuracy, and further provide insights into its feasibility. The merit of our method is demonstrated by both simulation studies and real examples.
主讲人简介
户文娟,首都经济贸易大学讲师,博士毕业于东北师范大学,圣路易斯华盛顿大学访问学者。主要研究方向是函数型数据和高维假设检验,研究成果主要发表在在Statistics and Computing,Acta,中国科学等期刊上。Sinica, 数学学报等期刊审稿人。
欢迎感兴趣的师生参加
校对| 王国长
责编| 彭 毅
初审| 姜云卢
终审发布| 何凌云
(来源:88858cc永利官网微信公众号)