Research
Working papers
Abstract
I propose a control function estimator for panel data models with weak instruments arising from nonlinear first stages. The estimator uses a Super Learner ensemble to approximate the optimal first stage, then inserts estimated control functions into a partially linear second stage. I establish √NT-consistency, Neyman orthogonality with respect to first-stage nuisance, and inference validity under the generated regressors problem (Pagan 1984, Murphy & Topel 1985). Monte Carlo simulations across varied DGPs confirm the estimator's robustness to library misspecification and overfitting.
Abstract
Empirical researchers routinely invoke the no-interference or individualistic treatment response (ITR) assumption to identify causal effects in observational studies, despite concerns that interference across units may arise in many economic settings. This paper studies the causal content of standard ITR-based identification formulas when arbitrary interference is present. We show that, under restrictions on dependence between treatment assignments across units, conventional ITR-based identification formulas---including those underlying selection-on-observables, instrumental variables, regression discontinuity designs, and difference-in-differences---identify well-defined causal objects: types of average direct effects (ADEs). These results do not require knowledge of the interference structure or specification of exposure mappings. We also propose a sensitivity analysis framework that quantifies the robustness of statistical inference to violations of treatment-assignment independence under arbitrary interference.
Work in progress
Publications
Presentations
| Year | Conference | Location |
|---|---|---|
| 2026 | European Causal Inference Meeting (EuroCIM 2026) | University of Oxford |