Some Advances of Causal Inference in Healthcare Research

Music City Center 

Understanding the impact of treatments on different populations is a fundamental challenge in causal inference. In this talk, we introduce a novel approach for estimating the Average Treatment Effect (ATE) and establish a direct connection to Individualized Treatment Rules (ITRs) using a scale-space matching framework. Our method refines treatment effect estimation by capturing variations across scales, enabling a more flexible and robust analysis of heterogeneous treatment effects. Through a series of simulations and real-world examples, we illustrate the advantages of our method in comparison to existing techniques. This work provides a new perspective on bridging global and personalized treatment effects, offering practical insights for data-driven decision-making in healthcare, policy evaluation, and other applied domains.