Sohrab Kordrostami - Academic member, Department of Applied Mathematics, Islamic Azad University, Lahijan, Iran,
Alireza Amirteimoori - Academic member, Department of Applied Mathematics, Islamic Azad University, Rasht, Iran,
Monireh Jahani Sayyad Noveiri - Ph. D. student, Islamic Azad University, Lahijan, Iran,

Input and output measures are usually precise in traditional data envelopment analysis (DEA) models. Moreover, inefficient decision making units (DMUs) can change input and output values arbitrarily so as to meet the efficient frontier. Nevertheless, occasions arise in the real world that data is not precise and data values cannot change arbitrarily. In fact, inputs and outputs variations are restricted by regarding limitations in resources and DMU‘s ability. For this purpose, in the current paper a model is proposed to evaluate the efficiency of DMUs where imprecise data and restrictions in variations exist. That is, variation levels of measures are predefined and imposed in a fuzzy DEA model. A numerical example illustrates the application of the suggested model.

Data envelopment analysis, Variation, Fuzzy numbers, Inputs, Outputs