Abstract:

Nowadays, DEA is more frequently used in performance evaluation actions. This method is a relative method to find optimal DMUs which are evaluated according to other DMUs. For obtaining the efficiency scores of DMUs, DEA bases on the ratio of the weighted sum of outputs to the weighted sum of inputs. In the computation of related ratio, DEA uses maximum efficiency scores to obtain different input and output weights of each DMU. In some situations, DEA cannot find reliable results, so that it gives same importance to each of inputs and outputs. For example, DEA evaluates most of DMUs as efficient, or assigns zero value as the weights for some outputs and inputs which are seen pretty important in reality. In this study, a weighted restricted model is used which is based on expert opinions and tries to shoot the mentioned troubles by AHP. As an application, the weighted restricted and weighted unrestricted DEA models are evaluated and the results are compared. In this study, the results which are derived from weighted unrestricted Model 1 and from weighted restricted Model 2 are given Table 4 and Table 8, respectively. In the evaluation of weighted restricted Model 2, the input/output weights are restricted with the aid of AHP method to allocate the weights homogeneously. According to the results, 12 departments by weighted unrestricted Model 1 and 3 departments by weighted restricted Model 2 are found efficient. Finally, it is found that input/ output weights by weighted restricted Model 2 are more homogeneous than weighted unrestricted Model 1.

Keywords: