Event Date
Event Date
Location
Mathematical Sciences Building 1147
Speaker: Natesh S. Pillai, Professor of Statistics, Harvard University
Title: A Heavily Right Strategy for Integrating Dependent Studies in Any Dimension
Abstract: Recently, there has been a surge of interest in hypothesis testing methods for combining dependent studies without explicitly assessing their dependence. Among these, the Cauchy combination test (CCT) stands out for its approximate validity and power, leveraging a heavy-tail approximation insensitive to dependence. However, CCT is highly sensitive to large p-values and inverting it to construct confidence regions can result in regions lacking compactness, convexity, or connectivity. In this talk, we will propose a "heavily right" strategy by excluding the left half of the Cauchy distribution in the combination rule, retaining CCT's resilience to dependence while resolving its sensitivity to large p-values.
Joint work with Tyler Liu and Xiao-Li Meng.
Bio: Natesh S. Pillai, is Professor of Statistics at Harvard University and was most recently a Distinguished Engineer at LinkedIn, where he worked on Responsible AI. He earned his PhD in Statistics from Duke University and his bachelor’s degree from Indian Institute of Technology. His research focuses on Computational methods, Bayesian inference, machine learning, and the statistical foundations of artificial intelligence. His work bridges probability, computation, and modern data science, with emphasis on developing theoretically grounded methods for reliable AI systems.
Faculty webpage. (external link)