In this paper, we employ the bias-adjusted matching estimator developed by Abadie and Imbens (2006), which overcomes this difficulty. The matching estimator analysis maps the multiple matching variables into a single number that measures the distance to the observation to be matched and selects as control observations those with the lowest value for this distance. Matching estimators, therefore, make it possible to use several matching variables simultaneously. 8 The bias-adjusted matching estimator of Abadie and Imbens further corrects the potential bias arising from the difference in the matching variables by explicitly taking into account how the variable of interest.
