Automated Local Regression Discontinuity Design Discovery
William Herlands (Carnegie Mellon University); Edward McFowland Iii (University of Minnesota); Andrew Wilson (Cornell University); Daniel Neill (Carnegie Mellon University)
Inferring causal relationships in observational data is crucial for understanding scientific and social processes. We develop the first statistical machine learning approach for automatically discovering regression discontinuity designs (RDDs), a quasi-experimental setup often used in econometrics. Our method identifies interpretable, localized RDDs in arbitrary dimensional data and can seamlessly compute treatment effects without expert supervision. By applying the technique to a variety of synthetic and real datasets, we demonstrate robust performance under adverse conditions including unobserved variables, substantial noise, and model.