Statistics Colloquium: Xianyang Zhang, Texas A&M University

This event is part of the Fall 2022 Statistics Colloquium

Powerful Large-scale Inference in Omics Association Studies

Presented by Xianyang Zhang, Associate Professor, Department of Statistics, Texas A & M University

Wednesday, October 5
4:00 p.m. ET
Philip E. Austin Building, Room 434

Increasing statistical power in analyzing omics data through methodological innovation is of tremendous benefit to the field due to resource constraints for individual studies. One direction of innovation is to utilize auxiliary data that could inform us of the statistical and biological properties of the omics features. The first part of the talk will introduce a new multiple testing procedure that can incorporate these auxiliary data to boost the statistical power. We develop a fast algorithm to implement the proposed procedure and prove its asymptotic validity. Through numerical studies, we demonstrate that the new approach improves over the state-of-the-art methods by being flexible, robust, powerful, and computationally efficient. The second part of the talk tackles the issue of statistical power loss when simultaneously adjusting for confounders and multiple testing in omics association studies. The traditional statistical procedure involves fitting a confounder-adjusted regression model for each omics feature, followed by multiple testing correction. Here we show that the conventional procedure is not optimal and present a new approach, 2dFDR, a two-dimensional false discovery rate control procedure, for powerful confounder adjustment in multiple testing. Through extensive evaluation, we show that 2dFDR is more powerful than the traditional procedure, and in the presence of strong confounding and weak signals, the power improvement could be more than 100%.

Speaker Bio:

Xianyang Zhang is an Associate Professor in the statistics department at Texas A&M University. He obtained his Ph.D. in statistics from the University of Illinois at Urbana Champaign in 2013. His research interests include high dimensional/large-scale statistical inference, kernel methods, genomics data analysis, functional data analysis, time series, and econometrics. He currently serves as an associate editor for Biometrics and Journal of Multivariate Analysis.