stat.MENov 9, 2026

Average versus expected causal effects under interference: Modeling assumptions and estimation bottlenecks

Authors: Vishesh Karwa, Edoardo M. Airoldi, Donald B. Rubin

Organizations: Department of Statistics, Operations, and Data Science, Temple University · Data Science Institute, Temple University, Philadelphia, PA 19122, USA · Department of Statistics, Harvard University, Cambridge, MA 02138, USA

Abstract

Causal inference under treatment interference requires assumptions to reduce the exponentially large number of potential outcomes. We develop hierarchical finite-population models for potential outcomes by separating these assumptions into three layers: interference neighborhoods, exposure mappings, and outcome models. Given an interference neighborhood and exposure mapping, we show that potential outcomes admit a nonparametric decomposition into direct, spillover, and treatment--spillover interaction components. This decomposition provides a common coordinate system for nonparametric, semiparametric, and parametric models of finite-population potential outcomes. For a given potential-outcome model, we define two classes of estimands. Average causal effects (ACEs), such as direct and total treatment effects, contrast potential outcomes under fixed treatment--exposure conditions. Expected causal effects (ECEs), such as expected direct and indirect effects, contrast expectations of potential outcomes under a specified allocation policy. For both classes, we bound the variance of the canonical Horvitz--Thompson estimator by three terms: a diagonal weight term, a term from overlapping interference neighborhoods, and a residual design-dependence term. Our upper and lower bounds show that under graph-unaware designs, nonparametric design-unbiased estimation of ACEs can require sample sizes growing exponentially in the interference degree, whereas polynomial growth can suffice for design-aligned ECEs. Under neighborhood interference, we construct graph-aware independent-set designs with variance bounds polynomial in the maximum degree for direct and total treatment effects on every graph, whereas graph cluster randomization can incur worst-case variance exponential in the degree.

Figures & tables

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Transportable Causal Effect Estimation across Networks under Interference

    Aug 19, 2026Xiaojing Du, Jiuyong Li, Lin Liu +3causal transportabilityCausal Effect Estimation

  2. Network Effect Decomposition for Causal Effect Estimation under Network Interference

    Nov 5, 2026Zhirong Huang, Wenzhen Zhang, Guangquan Lu +3Causal Effect EstimationCausal Inference

  3. Causal Inference for Sequential Settings under Interference and Latent Confounding

    Jul 16, 2026Phevos Paschalidis, Constantinos Daskalakis, Devavrat ShahCausal Effect EstimationCausal Inference with Unobserved Confounding