Sharing Inputs and Multicriteria Grouping of Dmus in DEA

Data envelopment analysis (DEA) is a methodology for evaluating the efficiencies of decision-making units (DMUs), with each unit having its own set of inputs and outputs. However, there are situations where the DMUs can be interdependent. The authors in previous papers examine the case of a single-stage problem, where multiple shared inputs are present and where subgroups of DMUs arise from those shared variables. As in previous studies, any shared resource is assumed to be one that cannot be split up and allocated to the group members. Unlike previous studies, the situation herein can involve having different DMU groupings in one stage than in another. In the current paper we consider the more general situation wherein a DEA-like methodology is developed to derive efficiency scores in a two-stage setting and in the presence of multiple attributes. To demonstrate the need for such a methodology, we examine the tourism sector in Mexico, where shared factors and groupings of DMUs need to be dealt with