A slacks-based measure of super-efficiency in data envelopment analysis

In most models of Data Envelopment Analysis, the best performers have the full efficient status denoted by unity (or 100%), and, from experience, we know that usually plural Decision Making Units (DMUs) have this ‘efficient status’. To discriminate between these efficient DMUs is an interesting subject. This paper addresses this ‘super-efficiency’ issue by using the slacks-based measure of efficiency, which the author proposed in his previous paper. The method differs from the traditional one based on the radial measure, e.g. Andersen and Petersen model, in that the former deals directly with slacks in inputs/outputs, while the latter does not take account of the existence of slacks. We will demonstrate the rationality of our approach by comparing it with the radial measure of super-efficiency. The proposed method will be particularly useful when the number of DMUs are small compared with the number of criteria employed for evaluation.