Average versus expected causal effects under interference: Modeling assumptions and estimation bottlenecks
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
| Representation | Target conditions | HT | LB | HT variance scale |
|---|---|---|---|---|
| Arbitrary interference | vs. | |||
| Neighborhood interference | vs. | |||
| Count/fraction exposure | vs. | |||
| Binary any-treated exposure | vs. |
| Representation | Target conditions | HT | LB | HT variance scale |
|---|---|---|---|---|
| Arbitrary interference | vs. | |||
| Neighborhood interference | vs. | |||
| Count/fraction exposure | vs. | |||
| Binary any-treated exposure | vs. |
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
| Graph sequence | ACE scale | EDE dependence |
|---|---|---|
| Bounded degree | ||
| Second-neighborhood regular, degree | ||
| Sparse Erdős–Renyi, mean degree | approximately | approximately |
| Dense block model, block size | approximately | approximately |
| Star graph | dominated by hub term | |
| Complete graph |
Causal Effect Estimation
Causal effect estimation measures how outcomes would change under interventions, using experiments or observational data and explicit assumptions.
See all 287 papers