Causal Inference on Networks under Misspecified Exposure Mappings: A Partial Identification Framework
This addresses robustness issues in network causal inference for researchers and practitioners, representing an incremental advance by applying sensitivity analysis to exposure mappings.
The paper tackles the problem of biased treatment effect estimates in network causal inference when exposure mappings are misspecified, by proposing a partial identification framework that derives sharp bounds on direct and spillover effects, with experiments showing the bounds remain informative under misspecification.
Estimating treatment effects in networks is challenging, as each potential outcome depends on the treatments of all other nodes in the network. To overcome this difficulty, existing methods typically impose an exposure mapping that compresses the treatment assignments in the network into a low-dimensional summary. However, if this mapping is misspecified, standard estimators for direct and spillover effects can be severely biased. We propose a novel partial identification framework for causal inference on networks to assess the robustness of treatment effects under misspecifications of the exposure mapping. Specifically, we derive sharp upper and lower bounds on direct and spillover effects under such misspecifications. As such, our framework presents a novel application of causal sensitivity analysis to exposure mappings. We instantiate our framework for three canonical exposure settings widely used in practice: (i) weighted means of the neighborhood treatments, (ii) threshold-based exposure mappings, and (iii) truncated neighborhood interference in the presence of higher-order spillovers. Furthermore, we develop orthogonal estimators for these bounds and prove that the resulting bound estimates are valid, sharp, and efficient. Our experiments show the bounds remain informative and provide reliable conclusions under misspecification of exposure mappings.