Robust DEA Models for Performance Evaluation of Systems with Continuous Uncertain Data under CRS and VRS Conditions

One of the most appropriate and efficient methods for evaluating the performance of homogenous decision-making units (DMU) is data envelopment analysis (DEA). Traditional DEA models are only able to evaluate DMUs with deterministic inputs and outputs, while in real-world problems, data are usually uncertain. So far, various approaches have been introduced to overcome the uncertainty of data. In this paper, two robust DEA models is presented to evaluate the performance of systems with continuous uncertain data under constant return to scale (CRS) and variable return to scale (VRS) conditions. The main advantage of the proposed robust DEA models over the previous robust DEA models is that they are able to formulate uncertainty in both input and output data. Moreover, these models are also developed directly on basic traditional DEA models (not alternative models). To demonstrate the applicability of two developed robust models, a numerical example is presented and the efficacy of models is exhibited.