Working Paper: NBER ID: w20773
Authors: Marinho Bertanha; Guido W. Imbens
Abstract: Many empirical studies use Fuzzy Regression Discontinuity (FRD) designs to identify treatment effects when the receipt of treatment is potentially correlated to outcomes. Existing FRD methods identify the local average treatment effect (LATE) on the subpopulation of compliers with values of the forcing variable that are equal to the threshold. We develop methods that assess the plausibility of generalizing LATE to subpopulations other than compliers, and to subpopulations other than those with forcing variable equal to the threshold. Specifically, we focus on testing the equality of the distributions of potential outcomes for treated compliers and always-takers, and for non-treated compliers and never-takers. We show that equality of these pairs of distributions implies that the expected outcome conditional on the forcing variable and the treatment status is continuous in the forcing variable at the threshold, for each of the two treatment regimes. As a matter of routine, we recommend that researchers present graphs with estimates of these two conditional expectations in addition to graphs with estimates of the expected outcome conditional on the forcing variable alone. We illustrate our methods using data on the academic performance of students attending the summer school program in two large school districts in the US.
Keywords: Fuzzy Regression Discontinuity; External Validity; Causal Inference
JEL Codes: C14
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| distributions of potential outcomes for treated compliers and always-takers are equal (C34) | expected outcome conditional on the forcing variable is continuous at the threshold (C24) |
| distributions of potential outcomes for non-treated compliers and never-takers are equal (C24) | expected outcome conditional on the forcing variable is continuous at the threshold (C24) |
| lack of a discontinuity in conditional expectations at the threshold (C24) | evidence against the violation of exogeneity assumptions (C20) |
| evidence against the violation of exogeneity assumptions (C20) | supports the external validity of the estimates (C13) |
| significant differences in academic performance based on compliance types (D29) | generalizability of the treatment effects (C90) |