Dynamic Regression Discontinuity: An Event-Study Approach

TL;DR

This paper introduces a new method for identifying and estimating dynamic treatment effects in regression discontinuity designs using an event-study approach, enabling clearer interpretation of intertemporal impacts.

Contribution

It develops a dynamic potential outcomes model and reformulates key assumptions to achieve point identification of impulse responses in RDDs, with a nonparametric estimation framework.

Findings

Effective estimation of dynamic effects of school expenditure on housing prices.

Method allows aggregation of effects over time and treatment paths.

Application demonstrates practical utility in policy analysis.

Abstract

I propose a novel argument to identify economically interpretable intertemporal treatment effects in dynamic regression discontinuity designs (RDDs). Specifically, I develop a dynamic potential outcomes model and reformulate two assumptions from the difference-in-differences literature, no anticipation and common trends, to attain point identification of cutoff-specific impulse responses. The estimand of each target parameter can be expressed as the sum of two static RDD contrasts, thereby allowing for nonparametric estimation and inference with standard local polynomial methods. I also propose a nonparametric approach to aggregate treatment effects across calendar time and treatment paths, leveraging a limited path independence restriction to reduce the dimensionality of the parameter space. I apply this method to estimate the dynamic effects of school district expenditure authorizations on housing prices in Wisconsin.