Robust and efficient statistical inference using data from diverse real-world sources

In this talk, I will discuss two projects aimed at leveraging data from multiple sources to derive generalizable evidence efficiently. In the first part, I will discuss a framework for robust inference in federated meta-learning, enabling inference for the prevailing model, defined as the one matching the majority of the sites. In the second part, I will present a framework for using external data available at the planning stage of a clinical trial to infer the efficiency gain from covariate adjustment in this future trial.

Speaker: Xiudi Li, PhD, Postdoctoral Research Fellow, Harvard University

Location: Mission Hall #2700 or via ZOOM (Register Here if attending via ZOOM)