Bandwidth Selection and the Estimation of Treatment Effects with Unbalanced Data

This paper addresses the selection of smoothing parameters for estimating the average treatment effect on the treated using matching methods. Because precise estimation of the expected counterfactual is particularly important in regions containing the mass of the treated units, we define and implement weighted cross-validation approaches that improve over conventional methods by considering the location of the treated units in the selection of the smoothing parameters. We also implement a locally varying bandwidth method that uses larger bandwidths in areas where the mass of the treated units is located. A Monte Carlo study compares our proposed methods to the conventional unweighted method and to a related method inspired by BERGEMANN et al. [2005]. The Monte Carlo analysis indicates efficiency gains from all methods that take account of the location of the treated units. We also apply all five methods to bandwidth selection in the context of the data from LALONDE'S [1986] study of the performance of non-experimental estimators using the experimental data from the National Supported Work (NSW) Demonstration program as a benchmark. Overall, both the Monte Carlo analysis and the empirical application show feasible precision gains for the weighted cross-validation and the locally varying bandwidth approaches.

[1]  Markus Frlich,et al.  Finite-Sample Properties of Propensity-Score Matching and Weighting Estimators , 2004, Review of Economics and Statistics.

[2]  James J. Heckman,et al.  Characterizing Selection Bias Using Experimental Data , 1998 .

[3]  O. Linton,et al.  Asymptotic Expansions for Some Semiparametric Program Evaluation Estimators , 2001 .

[4]  C. J. Stone,et al.  An Asymptotically Optimal Window Selection Rule for Kernel Density Estimates , 1984 .

[5]  C. Loader.  Bandwidth selection: classical or plug-in? , 1999 .

[6]  Jianqing Fan,et al.  Data‐Driven Bandwidth Selection in Local Polynomial Fitting: Variable Bandwidth and Spatial Adaptation , 1995 .

[7]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

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

[9]  J A Olson,et al.  Estimating derivatives of pharmacokinetic response curves with varying bandwidths. , 1995, Biometrics.

[10]  Petra E. Todd,et al.  Matching As An Econometric Evaluation Estimator: Evidence from Evaluating a Job Training Programme , 1997 .

[11]  R. Lalonde.  Evaluating the Econometric Evaluations of Training Programs with Experimental Data , 1984 .

[12]  G. Patil,et al.  Rejoinder , 2004, Environmental and Ecological Statistics.

[13]  Rajeev Dehejia.  Practical propensity score matching: a reply to Smith and Todd , 2005 .

[14]  N. L. Johnson,et al.  Continuous Univariate Distributions. , 1995 .

[15]  Qi Li.  Nonparametric econometrics , 2006 .

[16]  Jianqing Fan,et al.  Local Polynomial Regression: Optimal Kernels and Asymptotic Minimax Efficiency , 1997 .

[17]  Anton Flossmann.  Empirical Bias Bandwidth Choice for Local Polynomial Matching Estimators , 2008 .

[18]  M. C. Jones,et al.  A Brief Survey of Bandwidth Selection for Density Estimation , 1996 .

[19]  P. J. Green,et al.  Density Estimation for Statistics and Data Analysis , 1987 .

[20]  D. Rubin,et al.  The central role of the propensity score in observational studies for causal effects , 1983 .

[21]  D. Ruppert.  Empirical-Bias Bandwidths for Local Polynomial Nonparametric Regression and Density Estimation , 1997 .

[22]  Peter Kemper,et al.  The National Supported Work Demonstration , 1985 .

[23]  Theo Gasser,et al.  Finite-Sample Variance of Local Polynomials: Analysis and Solutions , 1996 .

[24]  J. Angrist,et al.  Choosing Among Alternative Nonexperimental Methods for Estimating the Impact of Social Programs : The Case of Manpower Training , 2007 .

[25]  J. Heckman.  Sample selection bias as a specification error , 1979 .

[26]  Peter Hall,et al.  On local smoothing of nonparametric curve estimators , 1996 .

[27]  Jianqing Fan.  Design-adaptive Nonparametric Regression , 1992 .

[28]  Rajeev Dehejia,et al.  Propensity Score-Matching Methods for Nonexperimental Causal Studies , 2002, Review of Economics and Statistics.

[29]  MARKUS FRÖLICH,et al.  Matching estimators and optimal bandwidth choice , 2005, Stat. Comput..

[30]  A. Bergemann,et al.  Evaluating the Dynamic Employment Effects of Training Programs in East Germany Using Conditional Difference-in-Differences , 2005, SSRN Electronic Journal.

[31]  Petra E. Todd,et al.  Matching As An Econometric Evaluation Estimator , 1998 .

[32]  Jeffrey A. Smith,et al.  Does Matching Overcome Lalonde's Critique of Nonexperimental Estimators? , 2000 .

[33]  D. Horvitz,et al.  A Generalization of Sampling Without Replacement from a Finite Universe , 1952 .

[34]  H. Müller,et al.  Variable Bandwidth Kernel Estimators of Regression Curves , 1987 .

[35]  Eva Herrmann,et al.  Local Bandwidth Choice in Kernel Regression Estimation , 1997 .

[36]  P. Hall.  Large Sample Optimality of Least Squares Cross-Validation in Density Estimation , 1983 .

[37]  G. Imbens,et al.  Efficient Estimation of Average Treatment Effects Using the Estimated Propensity Score , 2000 .

[38]  Thomas Lemieux,et al.  Labor Market Institutions and the Distribution of Wages, 1973-1992: A Semiparametric Approach , 1995 .

[39]  Jeffrey S. Racine,et al.  Cross-Validation and the Estimation of Conditional Probability Densities , 2004 .

[40]  D. Black,et al.  How robust is the evidence on the effects of college quality? Evidence from matching , 2004 .

[41]  Steven F. Lehrer,et al.  Matching using semiparametric propensity scores , 2013 .

[42]  James J Heckman,et al.  A Note on Adapting Propensity Score Matching and Selection Models to Choice Based Samples , 2009, The econometrics journal.