Empirical‐likelihood‐based difference‐in‐differences estimators

Summary. Recently there has been a surge in econometric and epidemiologic works focusing on estimating average treatment effects under various sets of assumptions. Estimation of average treatment effects in observational studies often requires adjustment for differences in pretreatment variables. Rosenbaum and Rubin have proposed the propensity score method for estimating the average treatment effect by adjusting pretreatment variables. In this paper, the empirical likelihood method is used to estimate average treatment effects on the treated under the difference‐in‐differences framework. The advantage of this approach is that the common marginal covariate information can be incorporated naturally to enhance the estimation of average treatment effects. Compared with other approaches in the literature, the method proposed can provide more efficient estimation. A simulation study and a real economic data analysis are presented.

[1]  Y. Vardi.  Empirical Distributions in Selection Bias Models , 1985 .

[2]  N. Matloff.  Use of regression functions for improved estimation of means , 1981 .

[3]  Lin Chen,et al.  Provably Fastest Parallel Algorithms for Bipartite Permutation Graphs , 1999, Parallel Process. Lett..

[4]  Jiahua Chen,et al.  Empirical likelihood estimation for ?nite populations and the e?ective usage of auxiliary informatio , 1993 .

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

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

[7]  J. Lawless,et al.  Empirical Likelihood and General Estimating Equations , 1994 .

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

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

[10]  G. Imbens,et al.  Implementing Matching Estimators for Average Treatment Effects in Stata , 2004 .

[11]  Jing Qin,et al.  Empirical Likelihood in Biased Sample Problems , 1993 .

[12]  Y. Vardi,et al.  Nonparametric Estimation in the Presence of Length Bias , 1982 .

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

[14]  A. Owen.  Empirical likelihood ratio confidence intervals for a single functional , 1988 .

[15]  O. Ashenfelter,et al.  Estimating the Effect of Training Programs on Earnings , 1976 .

[16]  G. Imbens,et al.  Combining Micro and Macro Data in Microeconometric Models , 1994 .

[17]  Alberto Abadie.  Semiparametric Difference-in-Differences Estimators , 2005 .

[18]  A. Owen.  Empirical Likelihood Ratio Confidence Regions , 1990 .

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