CMStatistics 2022: Start Registration
View Submission - CMStatistics
Title: A tree-based model averaging approach for personalized treatment effect estimation from heterogeneous data sources Authors:  Xiaoqing Tan - University of Pittsburgh (United States)
Chung-Chou Ho Chang - University of Pittsburgh (United States)
Ling Zhou - Southwestern University of Finance and Economics (China)
Lu Tang - University of Pittsburgh (United States) [presenting]
Abstract: Accurately estimating personalized treatment effects within a study site (e.g., a hospital) has been challenging due to the limited sample size. Furthermore, privacy considerations and a lack of resources prevent a site from leveraging subject-level data from other sites. We propose a tree-based model averaging approach to improve the estimation accuracy of conditional average treatment effects (CATE) at a target site by leveraging models derived from other potentially heterogeneous sites, without them sharing subject-level data. To our best knowledge, there is no established model averaging approach for distributed data with a focus on improving the estimation of treatment effects. Specifically, under distributed data networks, our framework provides an interpretable tree-based ensemble of CATE estimators that joins models across study sites, while actively modeling the heterogeneity in data sources through site partitioning. The performance of this approach is demonstrated by a real-world study of the causal effects of oxygen therapy on hospital survival rates and backed up by comprehensive simulation results.