Shenzhen University School of Mathematical Sciences
Liyuan Scholars Colloquium No. 125
Lecture Title: A Selective Overview of FDR Control Methods in High Dimensions and A New Stabilized eBH Method
Speaker: Zhong Wei (Professor, Xiamen University)
Date & Time: 4:30–5:30 PM, May 11, 2025
Venue: Classroom 1, Huixing Building, Yuehai Campus, Shenzhen University
Abstract: In this talk, I will first give a selective overview of False Discovery Rate (FDR) control methods, which provide a framework for controlling false signals in scientific discoveries. Numerous FDR control techniques, such as knockoff methods and data-splitting approaches, have been successfully developed and widely implemented in multiple testing and regression contexts. However, some of these methods can yield unstable results due to the inherent randomness of the algorithms. For instance, different constructions of knockoff copies can lead to different sets of selected variables. To enhance the stability and reproducibility of statistical outcomes, we propose a new unified stability approach for feature selection and multiple testing algorithms with FDR control, named Stabilized eBH. Our method aggregates e-values based on rank statistics generated from multiple runs of the base algorithm to construct stabilized e-values, which are then processed using the eBH procedure. This approach not only improves FDR control and power performance but also enhances the stability. It is adaptable and can be applied to most existing FDR control methods. Moreover, we investigate the theoretical properties of the stability method, including asymptotic FDR control, power enhancement, and stability guarantee. Extensive numerical experiments and applications to real datasets demonstrate that the proposed method generally outperforms existing alternatives.
Biography: Zhong Wei is a professor, Department Head, and Ph.D. supervisor in the Department of Statistics and Data Science, School of Economics, and Wang Yanan Institute for Studies in Economics, Xiamen University. He received his Ph.D. in Statistics from Pennsylvania State University in 2012. He is a recipient of the National Science Foundation for Distinguished Young Scholars (2019) and the Outstanding Young Scholar Award of Fujian Province (2019). His main research areas include statistical analysis of high-dimensional data, econometrics, and applications of statistics and data science. He serves as an associate editor for six journals, including Journal of the American Statistical Association (JASA). He has published (accepted) over 50 papers in authoritative domestic and international statistical journals such as AOS, JASA, JOE, JMLR, and Science China Mathematics. He has won the 9th Excellent Achievement Award for Scientific Research in Higher Education Institutions of China, the Baosteel Excellent Teacher Award, the Second Prize of the Young Scientists Award of the Fok Ying Tung Education Foundation, the Special Prize in the Teaching Skills Competition for Young Teachers of Xiamen University, and the title of "Top Ten Favorite Teachers" at Xiamen University, as well as the First Prize in the Teaching Innovation Competition of Xiamen University.
All faculty and students are welcome to attend!
School of Mathematical Sciences
May 7, 2025
