14 Pages Posted: 30 Mar 2009
Matching estimators are widely used in statistical data analysis. However, the distribution of matching estimators has been derived only for particular cases (Abadie and Imbens, 2006). This article establishes a martingale representation for matching estimators. This representation allows the use of martingale limit theorems to derive the asymptotic distribution of matching estimators. As an illustration of the applicability of the theory, we derive the asymptotic distribution of a matching estimator when matching is carried out without replacement, a result previously unavailable in the literature.
Keywords: matching, martingales, treatment effects, hot-deck imputation
JEL Classification: C13, C14, C21
Suggested Citation: Suggested Citation
Abadie, Alberto and Imbens, Guido W., A Martingale Representation for Matching Estimators. IZA Discussion Paper No. 4073. Available at SSRN: https://ssrn.com/abstract=1369819