主题：Sparse minimum distance kernel estimation for high-dimensional linear models
主讲人：王明秋 曲阜师范大学
主持人：王国长 暨南大学
时间：2025年7月4日（周五）下午15:40-16:40
地点：暨南大学石牌校区经济学院（中惠楼）102室
摘要
In recent years, the rapid advancement of data collection and processing technologies has led to an increasing influx of high-dimensional data into various scientific fields. However, this surge in data is often accompanied by the frequent occurrence of outliers, particularly in domains such as genomic and image data. If these outliers are not appropriately addressed, they can result in invalid estimated models that may mislead subsequent statistical inference based on the data. On the basis minimum distance and kernel density estimator, this paper thus proposes a new method named minimum distance kernel estimation (MDKE) to overcome the problems caused by the outliers in data. We construct the objective function of MDKE by employing the kernel technique. The merit of MDKE over existing approaches is that it is robust to both outliers and/or high-leverage points and does not rely on the density function of the response. Furthermore, the sparse MDKE (SMDKE) is proposed for high-dimensional data by inducing the regularizations such as LASSO, SCAD and MCP. The extensive simulation experiments are conducted, showing that the MDKE is more robust than the existing methods for data with outliers in both the response and covariates. Two examples of plasma beta-carotene level and microarray gene expression also demonstrate the merits of the SMDKE.
主讲人简介
王明秋，曲阜师范大学统计与数据科学学院教授，博士生导师。研究兴趣包括稳健估计、非参数统计推断、高维数据分析、大数据抽样等。中国现场统计研究会统计调查分会常务理事、山东省应用统计学会常务理事。先后多次前往香港大学、南方科技大学进行学术访问。先后主持国家自然科学基金面上项目等省部级以上项目7项。在国内外知名学术刊物《统计研究》、Statistics and Computing、Journal of Complexity等发表论文40余篇。担任Journal of the American Statistical Association、The American Statistician、Journal of Computational and Graphical Statistics、Statistics and Computing等杂志审稿人。
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：暨南大学经济学院微信公众号）
