The paper introduces Horvitz-Thompson estimators for edge-level causal effects under dyadic interference, a three-fold cross-fitting scheme to enable machine learning covariate adjustment, and a calibration step ensuring no asymptotic efficiency loss.
arXiv preprint arXiv:2411.00947 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
stat.ME 2years
2026 2representative citing papers
Under monotonicity of the conditional treatment effect in the propensity score, the overlap-weighted average treatment effect is bounded between the ATT and the ATC, with extensions to instrumental variables and beta weights.
citing papers explorer
-
Design-based edge-level causal inference with machine learning assisted covariate adjustment
The paper introduces Horvitz-Thompson estimators for edge-level causal effects under dyadic interference, a three-fold cross-fitting scheme to enable machine learning covariate adjustment, and a calibration step ensuring no asymptotic efficiency loss.
-
Introducing the CP-plot Based on Covariance Representations of Weighted Average Treatment Effects
Under monotonicity of the conditional treatment effect in the propensity score, the overlap-weighted average treatment effect is bounded between the ATT and the ATC, with extensions to instrumental variables and beta weights.