Efficient Estimation of Average Treatment Effects Under Treatment-Based Sampling, Second Version

51 Pages Posted: 30 May 2010

See all articles by Kyungchul Song

Kyungchul Song

University of British Columbia (UBC) - Department of Economics

Date Written: May 24, 2010

Abstract

Nonrandom sampling schemes are often used in program evaluation settings to improve the quality of inference. This paper considers what we call treatment-based sampling, a type of standard stratified sampling where part of the strata are based on treatment status. This paper establishes semiparametric efficiency bounds for estimators of weighted average treatment effects and average treatment effects on the treated. This paper finds that adapting the efficient estimators of Hirano, Imbens, and Ridder (2003) to treatment-based sampling does not always lead to an efficient estimator. This paper proposes efficient estimators that involve a different form of propensity score-weighting. Finally, this paper establishes an optimal design of treatment-based sampling that minimizes the semiparametric efficiency bound over the sampling designs.

Keywords: Treatment-Based Sampling, Standard Stratified Sampling, Semi-Parametric Efficiency, Treatment Effects, Optimal Sampling Designs

JEL Classification: C12,C14,C52

Suggested Citation

Song, Kyungchul, Efficient Estimation of Average Treatment Effects Under Treatment-Based Sampling, Second Version (May 24, 2010). PIER Working Paper No. 10-018, Available at SSRN: https://ssrn.com/abstract=1617262 or http://dx.doi.org/10.2139/ssrn.1617262

Kyungchul Song (Contact Author)

University of British Columbia (UBC) - Department of Economics

997-1873 East Mall
Vancouver, BC V6T 1Z1
Canada

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
66
Abstract Views
583
Rank
612,800
PlumX Metrics