Estimating Joint Treatment Effects by Combining Multiple Experiments

Estimating the effects of multi-dimensional treatments (i.e., joint treatment effects) is critical in many data-intensive domains, including genetics and drug evaluation. The main challenges for studying the joint treatment effects include the need for large sample sizes to explore different treatment combinations as well as potentially unsafe treatment interactions. In this paper, we develop machinery for estimating joint treatment effects by combining data from multiple experimental datasets. In particular, first, we develop new identification conditions for determining whether joint treatment effects can be expressed as a multidistribution adjustment formula. Further, we develop estimators with statistically appealing properties such as consistency and robustness to model misspecification and slow convergence. Finally, we perform simulation studies that corroborate the effectiveness of the proposed methods.