Ranking Decision-Making Units Using Double-Frontier Analysis ‎Approach

Data envelopment analysis is a nonparametric method for measuring the performance of a set of decision-making units (DMUs) that consume multiple inputs to produce multiple outputs. Using this approach, the performance of DMUs is measured from both optimistic and pessimistic views. However, their results are very misleading and even contradictory in many cases. Indisputably, different performance measures should be combined for an overall assessment of the performance of each DMU. This is known as double-frontier analysis. This article proposes a power-averaged efficiency measure to evaluate the overall performance of each DMU. The power-averaged efficiency combines both optimistic and pessimistic efficiencies of each DMU, ​​and therefore, is more comprehensive than both measures. The results showed the higher differentiation capability of the power-averaged efficiency than both optimistic and pessimistic efficiency measures. The efficiency of the proposed power-averaged efficiency was demonstrated through a numerical example on evaluation of the performance of 42 departments in one of the Islamic Azad University branches to reveal its capabilities in real life situations.