报告题目：Simultaneous Confidence Bands for the Error Distribution Function in Nonparametric Regression
报告人：王所进（Suojin Wang, Texas A&M University）
时间：2019年6月3日（星期一）下午4：00—5：00
地点：苏州大学本部精正楼（数学楼）二楼学术报告厅
摘要：Simultaneous confidence bands (SCBs) are constructed for the distribution of unobserved errors based on the empirical distribution function and kernel distribution estimator using residuals estimated from a nonparametric regression model. Our theoretical results show that the estimation error processes converge to a Gaussian process. Moreover, simulation experiments indicate that our proposed SCBs not only strike an intelligent balance between coverage probability and precision, but also achieve surprisingly as much as double efficiency of the classical infeasible SCBs. As an illustration, the proposed SCBs are applied to the Old Faithful geyser data for testing the error distribution.
报告人简介：
Dr. Suojin Wang is Associate Dean for Assessment in College of Science and a Professor of Statistics and Epidemiology & Biostatistics at Texas A&M University. He received his Ph.D. from the University of Texas at Austin. His research interests include semi- and non-parametric statistical methodology, missing and mis-measured data analyses, asymptotic theory, sample surveys, and applied statistics. He has over 160 peer-reviewed research publications. He was the Editor-in-Chief of Journal of Nonparametric Statistics during 2007-2012. He is an elected Fellow of the American Statistical Association, an elected Fellow of the Institute of Mathematical Statistics and an elected member of the International Statistical Institute. He received four major teaching awards from Texas A&M University, including the most prestigious University-level Distinguished Achievement Award in Teaching.
欢迎参加！