Technology Selection in The Presence of Both Cardinal and Ordinal Data

摘要: DATA ENVELOPMENT ANALYSIS (DEA) is a data-oriented approach for evaluating the performance of a set of peer entities called Decision making units (DMUs) whose performance is characterized by multiple measures. The definition of a DMU is generic and flexible. In our case, DMU refers to a technology. Selection of the best technology is an important phase for technology transfer. To selection the best technologies in the presence of both CARDINAL AND ORDINAL DATA, this paper proposes an innovative approach, which is based on DEA. This paper proposes to use “DEA with efficient and inefficient frontiers” for selection of the best technology in the presence of both CARDINAL AND ORDINAL DATA. In this approach, OPTIMISTIC AND PESSIMISTIC EFFICIENCIES of each technology are considered simultaneously. Compared with the traditional DEA, the DEA approach with efficient and inefficient frontiers can identify the best technology easily and accurately. A numerical example demonstrates the application of the proposed method.