estimating most productive scale size in dea under uncertainty

One of the important applications of data envelopment analysis (dea) is estimation of most productive scale size (mpss). the goal of this study, is to propose a new approach for estimating of mpss in the presence of uncertain data that only the upper and lower bounds of them are known. to reach this goal, robust optimization approach is applied for presenting robust counterpart of classic most productive scale size model under uncertainty situations. finally, a numerical example with uncertain input and output is employed to demonstrate applicability of the proposed robust mpss model.