In this paper we discuss the inverse data envelopment analysis(DEA) under weight restrictions. For this task we answer suchquestions: In a system of decision making units (DMUs) underevaluation, in the presence of weight restrictions, if a unitchanges some of its input (output) levels, to what extent shouldthe unit change outputs (inputs) such that its efficiency indexremains unchanged? We treat them as inverse data envelopmentanalysis problems under weight restrictions and propose a methodto answer such questions based on data envelopment analysis andmulti-objective linear programming (MOLP). Manuscript profile

In some realistic situations there may exist exogenously fixed or non-discretionary factors that are beyond the control of management and need to be considered. When an under-evaluated decision-making unit (DMU) is not included in the reference set of the original data envelopment analysis (DEA) models, the resulting DEA models are called super-efficiency DEA models. In this paper, by means of the modified Banker and Morey’s model, we show that the super-efficiency score can be decomposed into two data perturbation components of a particular test frontier decision-making unit and the remaining DMUs. In this means, we run a sensitivity analysis by specifying what perturbations of discretionary data can be tolerated before frontier DMUs become nonfrontier. Manuscript profile