Average Treatment Effects in the Presence of Interference

We propose a definition for the average indirect effect of a binary treatment in the potential outcomes model for causal inference. Our definition is analogous to the standard definition of the average direct effect, and can be expressed without needing to compare outcomes across multiple randomized experiments. We show that the proposed indirect effect satisfies a universal decomposition theorem, whereby the sum of the average direct and indirect effects always corresponds to the average effect of a policy intervention. We also consider a number of parametric models for interference considered by applied researchers, and find that our (non-parametrically defined) indirect effect remains a natural estimand when re-expressed in the context of these models.