A complete ranking of DMUs using restrictions in DEA models

Abstract

Data Envelopment Analyses (DEA) is a linear programming based method which evaluates relative efficiency of Decision Making Units (DMUs). It can include multiple outputs and inputs without a priori weights and without requiring explicit specification of functional forms between inputs and outputs. It computes a scalar measure of efficiency and determines efficient levels of inputs and outputs for each DMU under evaluation which has a range of zero to “1”; hence, it has the ability to rank DMUs, unless when some DMUs are the same in efficiency score, such as efficient DMUs or inefficient DMUs with the same efficiency score. In many cases, it is necessary to give a full ranking of the DMUs. Hence this paper introduces a new method for complete ranking of decision making units, which it does not need any changes in the models. Also, for presentation of the ability of this method, it is employed to rank the bank branch of a commercial bank branches in an empirical example.