External Validity in Fuzzy Regression Discontinuity Designs

Abstract Fuzzy regression discontinuity designs identify the local average treatment effect (LATE) for the subpopulation of compliers, and with forcing variable equal to the threshold. We develop methods that assess the external validity of LATE to other compliance groups at the threshold, and allow for identification away from the threshold. Specifically, we focus on the equality of outcome distributions between treated compliers and always-takers, and between untreated compliers and never-takers. These equalities imply continuity of expected outcomes conditional on both the forcing variable and the treatment status. We recommend that researchers plot these conditional expectations and test for discontinuities at the threshold to assess external validity. We provide new commands in STATA and MATLAB to implement our proposed procedures.

[1]  Guido Imbens,et al.  Why High-Order Polynomials Should Not Be Used in Regression Discontinuity Designs , 2014 .

[2]  Sandra E. Black.  Do better schools matter? Parental valuation of elementary education , 1999 .

[3]  Richard A. Berk,et al.  Capitalizing on Nonrandom Assignment to Treatments: A Regression-Discontinuity Evaluation of a Crime-Control Program , 1983 .

[4]  Matias D. Cattaneo,et al.  Randomization Inference in the Regression Discontinuity Design: An Application to Party Advantages in the U.S. Senate , 2015 .

[5]  Miikka Rokkanen,et al.  Wanna Get Away? Rd Identification Away from the Cutoff , 2012, SSRN Electronic Journal.

[6]  W. V. D. Klaauw,et al.  Estimating the Effect of Financial Aid Offers on College Enrollment: A Regression-Discontinuity Approach , 2002 .

[7]  Yingying Dong.  An Alternative Assumption to Identify LATE in Regression Discontinuity Designs , 2014 .

[8]  Justin McCrary,et al.  Manipulation of the Running Variable in the Regression Discontinuity Design , 2005 .

[9]  Alberto Abadie.  Bootstrap Tests for Distributional Treatment Effects in Instrumental Variable Models , 2002 .

[10]  Frederick Mosteller,et al.  Identification and estimation. , 1955 .

[11]  Extrapolate-Ing: External Validity and Overidentification in the Late Framework , 2010 .

[12]  J. Angrist,et al.  Identification and Estimation of Local Average Treatment Effects , 1994 .

[13]  R. Carter Hill.  Regression Discontinuity Designs , 2017 .

[14]  D. Black,et al.  Simple Tests for Selection: Learning More from Instrumental Variables , 2017, SSRN Electronic Journal.

[15]  J. Hahn,et al.  IDENTIFICATION AND ESTIMATION OF TREATMENT EFFECTS WITH A REGRESSION-DISCONTINUITY DESIGN , 2001 .

[16]  Max H. Farrell,et al.  Regression Discontinuity Designs Using Covariates , 2018, Review of Economics and Statistics.

[17]  Douglas L. Miller,et al.  Does Head Start Improve Children's Life Chances? Evidence from a Regression Discontinuity Design , 2005, SSRN Electronic Journal.

[18]  J. Angrist,et al.  Using Maimonides&Apos; Rule to Estimate the Effect of Class Size on Student Achievement , 1997 .

[19]  Thomas D. Cook,et al.  "Waiting for Life to Arrive": A history of the regression-discontinuity design in Psychology, Statistics and Economics , 2008 .

[20]  D. Campbell,et al.  Regression-Discontinuity Analysis: An Alternative to the Ex-Post Facto Experiment , 1960 .

[21]  Jordan D. Matsudaira.  Mandatory summer school and student achievement , 2008 .

[22]  Michal Kolesár,et al.  Simple and Honest Confidence Intervals in Nonparametric Regression , 2018 .

[23]  Yingying Dong.  Alternative Assumptions to Identify LATE in Fuzzy Regression Discontinuity Designs , 2018, Oxford Bulletin of Economics and Statistics.

[24]  David S. Lee.  Randomized experiments from non-random selection in U.S. House elections , 2005 .

[25]  Miikka A. T. Rokkanen,et al.  Exam Schools, Ability, and the Effects of Affirmative Action: Latent Factor Extrapolation in the Regression Discontinuity Design , 2015 .

[26]  J. Angrist,et al.  Identification and Estimation of Local Average Treatment Effects , 1995 .

[27]  Victor Lavy,et al.  Using Maimonides' Rule to Estimate the Effect of Class Size on Student Achievement , 1999 .

[28]  Sebastian Calonico,et al.  Robust Nonparametric Confidence Intervals for Regression‐Discontinuity Designs , 2014 .

[29]  Matias D. Cattaneo,et al.  Interpreting Regression Discontinuity Designs with Multiple Cutoffs , 2016, The Journal of Politics.

[30]  Matias D. Cattaneo,et al.  Robust Data-Driven Inference in the Regression-Discontinuity Design , 2014 .

[31]  David Albouy.  Do voters affect or elect policies? A new perspective, with evidence from the U.S. Senate , 2011 .

[32]  Joseph C Cappelleri,et al.  Regression Discontinuity Design , 2015, SAGE Research Methods Foundations.

[33]  Marinho Bertanha,et al.  Regression Discontinuity Design with Many Thresholds , 2017, Journal of Econometrics.

[34]  Jack Porter,et al.  Estimation in the Regression Discontinuity Model , 2003 .

[35]  Wilbert van der Klaauw.  Regression Discontinuity Analysis: A Survey of Recent Developments in Economics , 2008 .

[36]  Joshua D. Angrist,et al.  Treatment Effect Heterogeneity in Theory and Practice , 2003 .

[37]  William Orlando Escobar-Caicedo.  Determinantes del uso y cantidad de uso de derivados financieros en las empresas no financieras listadas en la Bolsa de Valores de Colombia , 2020 .

[38]  Erich Battistin,et al.  Ineligibles and eligible non-participants as a double comparison group in regression-discontinuity designs , 2008 .

[39]  David S. Lee,et al.  Do Voters Affect or Elect Policies? Evidence from the U. S. House , 2004 .

[40]  J. Angrist,et al.  Does Compulsory School Attendance Affect Schooling and Earnings? , 1990 .

[41]  Ismael Mourifié,et al.  Testing identifying assumptions in fuzzy regression discontinuity designs , 2016, Quantitative Economics.

[42]  Rafael Lalive,et al.  How Do Extended Benefits Affect Unemployment Duration? A Regression Discontinuity Approach , 2006, SSRN Electronic Journal.

[43]  Joshua D. Angrist,et al.  Wanna Get Away? Regression Discontinuity Estimation of Exam School Effects Away From the Cutoff , 2015 .

[44]  Stefan Wager,et al.  Optimized Regression Discontinuity Designs , 2017, Review of Economics and Statistics.

[45]  David S. Lee,et al.  Regression Discontinuity Designs in Economics , 2009 .

[46]  Otávio Bartalotti,et al.  Bootstrap Confidence Intervals for Sharp Regression Discontinuity Designs , 2017 .

[47]  Arthur Lewbel,et al.  Identifying the Effect of Changing the Policy Threshold in Regression Discontinuity Models , 2015, Review of Economics and Statistics.

[48]  J. Hausman.  Specification tests in econometrics , 1978 .

[49]  B. Efron,et al.  Bootstrap confidence intervals , 1996 .

[50]  Martin Huber,et al.  Testing Instrument Validity for LATE Identification Based on Inequality Moment Constraints , 2015, Review of Economics and Statistics.

[51]  W. V. D. Klaauw,et al.  Regression-Discontinuity Analysis: A Survey of Recent Developments in Economics , 2008 .

[52]  Joshua D. Angrist,et al.  Identification of Causal Effects Using Instrumental Variables , 1993 .

[53]  Matias D. Cattaneo,et al.  Optimal Data-Driven Regression Discontinuity Plots , 2015 .

[54]  Erich Battistin,et al.  Counting Rotten Apples: Student Achievement and Score Manipulation in Italian Elementary Schools , 2014, SSRN Electronic Journal.