Tightening Input-Output Intervals in Imprecise Data Envelopment Analysis

Data envelopment analysis (DEA) [1] is a non-parametric method for evaluating the relative effi-ciency of decision-making units (DMU) on the basis of multiple inputs and outputs. The original DEA models assume that inputs and outputs are mea-sured by exact values on a ratio scale. Cooper et al. [2] addressed the problem of imprecise data in DEA (IDEA) in its general form. The term ”im-precise data ” reflects the situation where some of the input and output data are only known to lie within bounded intervals (interval numbers) while other data are known only up to an order. Despo-tis and Smirlis [3] proposed an alternative approach for dealing with imprecise data. They transforme