A New Method for Improving the Discrimination Power and Weights Dispersion in the Data Envelopment Analysis

The appropriate choice of input-output weights is necessary to have a successful DEA model. Generally, if the number of DMUs i.e., n, is less than number of inputs and outputs i.e., m+s, then many of DMUs are introduced as efficient then the discrimination between DMUs is not possible. Besides, DEA models are free to choose the best weights. For resolving the problems that are resulted from freedom of weights, some constraints are set on the input-output weights. Symmetric weight constraints are a kind of weight constrains. In this paper, we represent a new model based on a multi-criterion data envelopment analysis (MCDEA) are developed to moderate the homogeneity of weights distribution by using symmetric weight constrains. Consequently, we show that the improvement of the dispersal of unrealistic input-output weights and the increasing discrimination power for our suggested models. Finally, as an application of the new model, we use this model to evaluate and ranking guilan selected hospitals.