Regression Discontinuity Threshold Optimization

30 Pages Posted: 4 Mar 2019 Last revised: 24 Jun 2021

See all articles by Ioana Elena Marinescu

Ioana Elena Marinescu

University of Pennsylvania - School of Social Policy & Practice; National Bureau of Economic Research (NBER)

Sofia Triantafillou

University of Pittsburgh - Department of Biomedical Informatics

Konrad Kording

University of Pennsylvania

Date Written: February 12, 2019

Abstract

Treatments often come with thresholds, e.g. we are given statins if our cholesterol is above a certain threshold. But which statin administration threshold maximizes our quality of life adjusted years? More generally, which threshold would optimize the average expected outcome? Regression discontinuity approaches are used to measure the local average treatment effect (LATE) and more recently also the Marginal Threshold Treatment Effect (MTTE), which shows how marginal changes in the threshold can affect the LATE. We extend this idea to define the problem of optimizing a policy threshold, i.e. selecting a threshold that optimizes the cumulative effect of the treatment on the treated. We present an estimator of the optimal threshold based on a constrained optimization framework. We show how to use machine learning (Gaussian process regression) for non-linear estimation. We also extend the estimation to a conservative threshold that is unlikely to produce harm, and we show how to include policy cost constraints. We apply these results to estimate an optimal tip-maximizing threshold for tip suggestions in taxi cabs (Haggag and Paci, 2014).

Keywords: regression discontinuity, optimization, program evaluation

JEL Classification: C21, C31

Suggested Citation

Marinescu, Ioana Elena and Triantafillou, Sofia and Kording, Konrad, Regression Discontinuity Threshold Optimization (February 12, 2019). Available at SSRN: https://ssrn.com/abstract=3333334 or http://dx.doi.org/10.2139/ssrn.3333334

Ioana Elena Marinescu (Contact Author)

University of Pennsylvania - School of Social Policy & Practice ( email )

3701 Locust Walk
Philadelphia, PA 19104-6214
United States

National Bureau of Economic Research (NBER) ( email )

1050 Massachusetts Avenue
Cambridge, MA 02138
United States

Sofia Triantafillou

University of Pittsburgh - Department of Biomedical Informatics ( email )

5607 Baum Boulevard, Suite 500
Pittsburgh, PA 15206-3701
United States

Konrad Kording

University of Pennsylvania ( email )

Philadelphia, PA 19104
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
220
Abstract Views
1,513
rank
189,009
PlumX Metrics