Robust Russell and enhanced Russell measures in DEA

Abstract

Russell measure is among non-radial measures for efficiency evaluation of decision making units in data envelopment analysis. Due to the nonlinearity of its objective function, an enhanced version of it is proposed that can be linearized using the known Charnes-Cooper change of variables. In this article, we give equivalent formulations of the robust Russell measure and its enhanced models under interval and ellipsoidal uncertainties in their best- and worst-cases. We show that the built formulations stay convex for both best- and worst-cases under interval uncertainty as well as worst-case with ellipsoidal uncertainty. In other words, these formulations are nonconvex only for ellipsoidal uncertainty in their best-case. Some illustrative examples are provided to validate the new models.