This is particularly relevant because estimated differences between SRI and conventional funds may not be due to the socially responsible investing per se, but to differences between the companies that manage SRI funds and those that manage conventional funds. Finally, we improve upon the matched-pair analysis employed in several prior studies by using the matching estimator methodology of Abadie and Imbens (2006). This methodology provides a systematic procedure to find matches when matching is done on several variables simultaneously, as well as a method to adjust for the bias that arises when matches with identical values of the matching.
