Pacific AB
Causal estimation of scaled treatment effects with multiple outcomes in a community health worker study (306434)
Edward Kennedy, Carnegie Mellon University*Nandita Mitra, University of Pennsylvania
Keywords: causal inference, multiple outcomes, influence functions
Typical study designs aim to learn about the effects of an intervention on a single outcome; in many clinical studies, however, data on multiple outcomes are collected and it is of interest to explore effects on multiple outcomes simultaneously. Such designs can be particularly useful in patient-centered research, where different outcomes might be more or less important to different patients. We propose scaled effect measures (via potential outcomes) that translate effects on multiple outcomes to a common scale, using mean-variance and median-interquartile range based standardizations. We present efficient, nonparametric, doubly robust methods for estimating these scaled effects and for testing the null hypothesis that treatment affects all outcomes equally. We also discuss methods for exploring how treatment effects depend on covariates. Our methods are nonparametric and can be used not only in randomized trials to yield increased efficiency, but also in observational studies with high-dimensional covariates to reduce confounding bias. We illustrate these methods using data from a community health worker study in Philadelphia which resulted in a policy shift at the hospital level.