ranking efficient units in dea by using malmquist productivity index

Since in evaluating by traditional data envelopment analysis (dea) models, many decision making units (dmus) are classified as efficient, it is necessary to give a full ranking of the dmus. since none of the ranking methods have used the malmquist productivity index (mpi) for ranking efficient dmus, this paper introduces a new method for ranking dmus which is based on the omission of the efficient dmus from the production possibility set (pps) in two time periods t and t + 1 and measuring the magnitude of their influence on the mpi of the other dmus. also, one of the advantages of the presented approach is ranking extreme and non-extreme dmus simultaneously in many cases. a numerical example confirms the validity of the proposed method.