Symmetric Constraint of Units with Interval Data in DEA

ABSTRACT: The conventional DEA assumes that data on the outputs and inputs are known exactly. However in many real applications, we confront cases in which the input/output data belong to intervals, the DEA models becomes a nonlinear programming problem and is called imprecise DEA (IDEA). Also, interval data envelopment analysis models are free to choose the best weights. There is limited method for choosing constrain weight, one kind of weight constrains that proposed by Dimitrov and Sutton (2008) is symmetric weight constrain. In this paper, we applied symmetric weight constraints in DEA models with interval data, it let corresponding weights with interval inputs and outputs become symmetric and nonzero.