YSPH Biostatistics Seminar: “A Model-free Variable Screening Method Based on Leverage Score”

NOTE: BIS 525 students are required to attend in person. Others are invited to attend in person, but may also attend via Zoom.

SPEAKER: Yiwen Liu, PhD, Assistant Professor, Department of Epidemiology and Biostatistics, University of Arizona

TITLE: “A Model-free Variable Screening Method Based on Leverage Score"

ABSTRACT: Massive datasets have been collected in many fields of science, such as biology, chemistry, and engineering. The inadequate sample is no longer a bottleneck of modern statistical research. More often, we are facing data of extremely high dimensionality. How to effectively extract information from high-dimensional data poses new statistical challenges. In this talk, I will introduce a weighted leverage score (WLS) method for variable screening. The predictors selected using the WLS can consistently exclude redundant predictors not only for linear models but also for general index models. The screening consistency using the WLS will be discussed to provide theoretical underpinnings of the proposed method. I will highlight in this talk the application of the method for identifying carcinoma-related genes using spatial transcriptome data.