Dealing with endogeneity in data envelopment analysis applications

Although the presence of the endogeneity is frequently observed in economic production processes, it tends to be overlooked when practitioners apply data envelopment analysis (DEA). In this paper we deal with this issue in two ways. First, we provide a simple statistical heuristic procedure that enables practitioners to identify the presence of endogeneity in an empirical application. Second, we propose the use of an instrumental input DEA (II-DEA) as a potential tool to address this problem and thus improve DEA estimations. A Monte Carlo experiment confirms that the proposed II-DEA approach outperforms standard DEA in finite samples under the presence of high positive endogeneity. To illustrate our theoretical findings, we perform an empirical application on the education sector.