Professor Fan Li seminar 19.8

Assoc. Prof. Fan Li (Dept of Statistical Science, Duke University):

CAUSAL INFERENCE WITH REGRESSION CONTINUITY DESIGNS

Abstract: Regression discontinuity (RD) designs are often interpreted as local randomized experiments: a RD design can be considered as a randomized experiment for units with a realized value of a so-called forcing variable falling around a pre-fixed threshold. In this paper, we propose a probabilistic formulation of the assignment mechanism underlying RD designs within the Rubin Causal Model. We use the principal stratification framework to define causal estimands for fuzzy RD. We also develop a model-based Bayesian approach to select the target subpopulation(s) and draw inference. Applying the method to the data from two Italian universities, we find evidence that university grants are effective in preventing students from low-income families from dropping out of higher education.

Place and time: Quantum (Sali 284), 2.krs 19.8. klo 14.00