The Devil is in the Tails: Regression Discontinuity Design with Measurement Error in the Assignment Variable

Identification in a regression discontinuity (RD) design hinges on the discontinuity in the probability of treatment when a covariate (assignment variable) exceeds a known threshold. If the assignment variable is measured with error, however, the discontinuity in the first stage relationship between the probability of treatment and the observed mismeasured assignment variable may disappear. Therefore, the presence of measurement error in the assignment variable poses a challenge to treatment effect identification. This paper provides sufficient conditions for identification when only the mismeasured assignment variable, the treatment status and the outcome variable are observed. We prove identification separately for discrete and continuous assignment variables and study the properties of various estimation procedures. We illustrate the proposed methods in an empirical application, where we estimate Medicaid takeup and its crowdout effect on private health insurance coverage.

[1]  Thomas Le Barbanchon,et al.  Regression Discontinuity Design with Continuous Measurement Error in the Running Variable , 2017, SSRN Electronic Journal.

[2]  Yingying Dong,et al.  Regression Discontinuity Applications with Rounding Errors in the Running Variable , 2015 .

[3]  Takahide Yanagi,et al.  The Effect of Measurement Error in the Sharp Regression Discontinuity Design , 2014 .

[4]  Henrik Jacobsen Kleven,et al.  Using Notches to Uncover Optimization Frictions and Structural Elasticities: Theory and Evidence from Pakistan* , 2013 .

[5]  Thomas G. Koch.  Using RD design to understand heterogeneity in health insurance crowd-out. , 2013, Journal of health economics.

[6]  Alan Barreca,et al.  Saving babies? Revisiting the effect of very low birth weight classification. , 2011, The quarterly journal of economics.

[7]  Heidi L. Williams,et al.  The role of hospital heterogeneity in measuring marginal returns to medical care: a reply to Barreca, Guldi, Lindo, and Waddell. , 2011, The quarterly journal of economics.

[8]  Alan I. Barreca,et al.  Heaping‐Induced Bias in Regression‐Discontinuity Designs , 2011 .

[9]  Matthias Kohl,et al.  General Purpose Convolution Algorithm in S4 Classes by Means of FFT , 2010, 1006.0764.

[10]  T. Klein,et al.  The Effect of Private Health Insurance on Medical Care Utilization and Self-Assessed Health in Germany , 2010, Health economics.

[11]  Sébastien Van Bellegem,et al.  Consistent Density Deconvolution under Partially Known Error Distribution , 2010 .

[12]  A. Lewbel,et al.  Nonparametric identification of a binary random factor in cross section data , 2009 .

[13]  D. Schanzenbach.  Do School Lunches Contribute to Childhood Obesity? , 2009, The Journal of Human Resources.

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

[15]  Heidi L. Williams,et al.  Estimating Marginal Returns to Medical Care: Evidence from At-Risk Newborns , 2008, The quarterly journal of economics.

[16]  P. Schmidt,et al.  GMM with more moment conditions than observations , 2008 .

[17]  L. Shore-Sheppard,et al.  Stemming the Tide? The Effect of Expanding Medicaid Eligibility On Health Insurance Coverage , 2008 .

[18]  G. Weber,et al.  The Retirement Consumption Puzzle: Evidence from a Regression Discontinuity Approach , 2007 .

[19]  Xiaohong Chen,et al.  Nonparametric identification and estimation of nonclassical errors-in-variables models without additional information , 2007 .

[20]  Arthur Lewbel,et al.  Estimation of Average Treatment Effects With Misclassification , 2007 .

[21]  Aprajit Mahajan,et al.  Identification and Estimation of Regression Models with Misclassification , 2005 .

[22]  David Card,et al.  The Measurement of Medicaid Coverage in the SIPP , 2004 .

[23]  David Card,et al.  Using Discontinuous Eligibility Rules to Identify the Effects of the Federal Medicaid Expansions on Low-Income Children , 2004, Review of Economics and Statistics.

[24]  David Ruppert,et al.  Local polynomial regression and simulation–extrapolation , 2004 .

[25]  Scott M. Berry,et al.  Bayesian Smoothing and Regression Splines for Measurement Error Problems , 2002 .

[26]  Lara D. Shore-Sheppard,et al.  Using Discontinuous Eligibility Rules to Identify the Effects of the Federal Medicaid Expansions , 2001 .

[27]  M. Berger,et al.  Bounding Parameter Estimates with Nonclassical Measurement Error , 2000 .

[28]  Emmanuel Saez,et al.  Do Taxpayers Bunch at Kink Points? , 1999 .

[29]  D. Ruppert,et al.  Nonparametric regression in the presence of measurement error , 1999 .

[30]  Donald W. K. Andrews,et al.  Semiparametric Estimation of the Intercept of a Sample Selection Model , 1998 .

[31]  R. Kaestner,et al.  Medicaid Expansions and the Crowding Out of Private Health Insurance , 1998, Inquiry : a journal of medical care organization, provision and financing.

[32]  J. Gruber,et al.  Does Public Insurance Crowd Out Private Insurance? , 1995 .

[33]  J. R. Cook,et al.  Simulation-Extrapolation Estimation in Parametric Measurement Error Models , 1994 .

[34]  Orley Ashenfelter,et al.  Estimates of the Economic Return to Schooling from a New Sample of Twins , 1992 .

[35]  Hidehiko Ichimura,et al.  Identification and estimation of polynomial errors-in-variables models , 1991 .

[36]  A. Chesher.  The effect of measurement error , 1991 .

[37]  F. Palm,et al.  Asymptotic Least-Squares Estimation Efficiency Considerations and Applications , 1990 .

[38]  John M. Abowd,et al.  The Review of Economics and Statistics , 2013 .

[39]  D. de la Mata,et al.  The effect of Medicaid eligibility on coverage, utilization, and children's health. , 2012, Health economics.

[40]  C. S. Reichardt,et al.  Regression-discontinuity designs. , 2012 .

[41]  Jeffrey C. Moore,et al.  Measurement Errors in SIPP Program Reports , 2010 .

[42]  Qi Li,et al.  Nonparametric Econometrics: Theory and Practice , 2006 .

[43]  Susanne M. Schennach,et al.  Estimation of Nonlinear Models with Measurement Error , 2004 .

[44]  Catherine Matias,et al.  SEMIPARAMETRIC DECONVOLUTION WITH UNKNOWN NOISE VARIANCE , 2002 .

[45]  John Bound,et al.  Measurement error in survey data , 2001 .

[46]  Petra E. Todd,et al.  IDENTIFICATION AND ESTIMATION OF TREATMENT EFFECTS WITH A REGRESSION-DISCONTINUITY DESIGN , 2001 .

[47]  N. Bates,et al.  Using administrative records to assess earnings reporting error in the survey of income and program participation , 2000 .

[48]  Tong Li,et al.  Nonparametric Estimation of the Measurement Error Model Using Multiple Indicators , 1998 .

[49]  K. Thorpe,et al.  Health insurance among children: the role of expanded Medicaid coverage. , 1998, Inquiry : a journal of medical care organization, provision and financing.