Improved inference for doubly robust estimators of heterogeneous treatment effects

• Published in: Biometrics Vol. 79; no. 4; pp. 3140 - 3152
• Main Authors: Shin, Heejun, Antonelli, Joseph
• Format: Journal Article
• Language: English
• Published: United States Blackwell Publishing Ltd 01.12.2023
• Subjects: Bayesian nonparametrics; causal inference; Causality; Computer Simulation; doubly robust estimation; environmental exposure; Epidemiology; Heterogeneity; high‐dimensional statistics; Inference; Models, Statistical; National Health and Nutrition Examination Survey; Nutrition Surveys; Observational studies; Propensity Score; Regression analysis; Regression models; Robustness; Treatment Effect Heterogeneity; variance; Variance analysis; treatment effect heterogeneity; Bayesian nonparametrics; causal inference; high-dimensional statistics; doubly robust estimation
• ISSN: 0006-341X; 1541-0420; 1541-0420
• DOI: 10.1111/biom.13837

We propose a doubly robust approach to characterizing treatment effect heterogeneity in observational studies. We develop a frequentist inferential procedure that utilizes posterior distributions for both the propensity score and outcome regression models to provide valid inference on the conditiona...