时 间：2026年5月9 日（周六）15：00 - 16：00
报告人：崔跃华 Michigan State University教授
地 点：普陀校区理科大楼A1514室
邀请人：史兴杰 华东师范大学副教授
摘 要：
Mendelian randomization (MR) leverages genetic variants as instrumental variables (IVs) to estimate causal effects using observational data. In this talk, I will present some of our recent work on one-sample MR analysis. I will first introduce MR-SPLIT, a framework that mitigates bias from IV selection and weak instruments by separating instrument selection and effect estimation within a data-splitting scheme. I will then present MR-SPLIT+, an extension that identifies IVs that may violate the exclusion-restriction assumption due to genetic pleiotropy. Together, these approaches illustrate how instrumental variable methods can be adapted to enhance robustness and interpretability in modern MR applications.
报告人简介：
Yuehua Cui is a Professor in the Department of Statistics and Probability at MSU. His research focuses on statistical genetics and genomics. He has published extensively in leading journals such as Nature Communications, Advanced Science, JRSS-B, AOAS and Biometrics. He is an elected Fellow of the American Statistical Association (ASA) and an elected member of the International Statistical Institute (ISI). He currently serves as an Academic Editor for PLOS Genetics and PLOS Computational Biology, and an Associate Editor for several journals in statistics and computational genomics including Statistics and Probability Letters and Statistical Applications in Genetics and Molecular Biology.