Selected Research
Abstract
I propose a control function estimator for panel data models with weak instruments due to nonlinear first stages. The estimator combines a Super Learner ensemble for the first stage with semiparametric efficiency theory, achieving √NT-consistency and Neyman orthogonality in the presence of generated regressors. Monte Carlo simulations confirm finite-sample performance across a range of DGPs.
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.
Fields
Education & positions
| 2022 – present | Postdoctoral Researcher in Statistics, Methods and Data Analysis,University of Geneva |
| 2023 – 2025 | Assistant Professor in Econometrics, Econometrics Group, University of Bristol |
| 2016 – 2022 | PhD in Econometrics, University of Geneva |
Community
- Founding member, R-Ladies Geneva
- Mentor, rOpenSci Champions Program 2026