Estimation and Inference for Counterfactual Treatment Effects

Assistant Professor, Department of Economics, Feng Chia University.

Prof. Lai' CV.

This paper proposes statistical methods to evaluate the quantile counterfactual treatment effect(QCTE) when the composition of the population targeted by the status quo program was changed. The QCTE enables us to carry out an ex-ante assessment of distributional impacts of policy interventions, or conduct a meta-analysis to investigate possible explanations for treatment effect heterogeneity. Assuming unconfoundedness and the invariance of the conditional distributions of the potential outcomes, the QCTE is identified and can be nonparametrically estimated by a kernel-based method. Viewed as a random function over the continuum of quantile indices, the estimator converges weakly to a zero mean Gaussian process at the parametric rate. We then propose a multiplier bootstrap procedure to construct uniform confidence bands and provide similar results for the counterfactually treated subpopulation and the average effects. As an empirical application, we estimate the QCTE of the Job Corps training program in the U.S. under various scenarios. Our results suggest that the strong economic performance indeed explains the earlier finding in the literature that the program was ineffective at low quantiles of the earnings distribution. However, no supportive evidence is found for the skill hypothesis.