A0802
Title: Semiparametric causal mediation analysis in cluster-randomized experiments
Authors: Fan Li - Yale University (United States) [presenting]
Chao Cheng - Yale School of Public Health (United States)
Abstract: In cluster-randomized experiments, there is emerging interest in exploring the causal mechanism in which a cluster-level treatment affects the outcome through an intermediate outcome. The formal semiparametric efficiency theory is developed to motivate several doubly robust methods for addressing several mediation effect estimands corresponding to both the cluster-average and the individual-level treatment effects in cluster-randomized experiments: the natural indirect effect, natural direct effect, and spillover mediation effect. The efficient influence function is derived for each mediation effect, and carefully parameterize each efficient influence function to motivate practical strategies for operationalizing each estimator. Parametric working models and data-adaptive machine learners are considered to estimate the nuisance functions and obtain semiparametric efficient causal mediation estimators in the latter case. The methods are illustrated via extensive simulations and two completed cluster-randomized experiments.
