A very small positive constant (generally taken to be 1.0E-6) whose purpose in the primal model, Epsilon prevents any factor from being abused as a free commodity and avoid a unit being falsely classified as efficient. In the dual model, epsilon’s role is to make sure that the minimisation of the intensity factor, takes precedence over the maximisation of the sum of the slacks. The value of epsilon may cause computational inaccuracies, a solution is provided in Ali and Seiford (1993). Ali A and Seiford L (1993), ‘The mathematical programming approach to efficiency analysis’, in: Fried H, Knox C A K and Schmidt S (editors), The measurement of productive efficiency: techniques and applications, Oxford University Press.

Leave a Reply