Primary Submission Category: Heterogeneous Treatment Effects
Adaptive Experiments Toward Learning Treatment Effect Heterogeneity
Authors: Waverly Wei, Jingshen Wang,
Presenting Author: Waverly Wei*
Understanding treatment effect heterogeneity has become an increasingly popular task in various fields. For example, in e-commerce, understanding treatment effect heterogeneity helps decision-makers to design personalized advertising strategies to maximize profits. In biomedical studies, learning the impact of treatment on diverse patient subpopulations provides insights for personalized care. While much of the existing work in this research area has focused on either analyzing observational data based on untestable causal assumptions or conducting post hoc analyses of existing randomized controlled trial data, little work has gone into designing randomized experiments specifically for uncovering treatment effect heterogeneity. In this work, we develop a unified adaptive experimental design framework towards better learning treatment effect heterogeneity by efficiently identifying subpopulations with enhanced treatment effects. The adaptive nature of our framework allows practitioners to sequentially allocate experimental efforts adapting to the accrued evidence during the experiment. The resulting design framework can not only complement A/B tests in e-commerce but also unify enrichment designs and response adaptive randomization designs in clinical settings. Our theoretical investigations illustrate the trade-offs between complete randomization and our adaptive experimental algorithms. We also investigate our design in simulation studies and e-commerce data analysis.