Ghasemi, M. R., J. Ignatius; A. Emrouznejad (2014) “A bi-objective weighted model for improving the discrimination power in MCDEA”, European Journal of Operational Research, 233 (3): 640–650.
Lack of discrimination power and poor weight dispersion remain major contention issues in Data Envelopment Analysis (DEA) models, which have also hampered the developments in the multiobjective DEA domain. Since the initial multi- criteria DEA (MCDEA) model of Li and Reeves ( 1999), only one other research by Bal, Örkcü and Çelebio?lu ( 2010) attempted to solve the MCDEA framework through two goal programming approaches, i.e. GPDEA-CCR and GPDEA-BCC. It was claimed that both models improved upon the discrimination power of DEA by balancing the distribution of input-output weights. It was also claimed that both GPDEA models are major improvements to the original MCDEA of Li and Reeves (1999). In this research we first checked the validity of GPDEA models and found that they do not improve the discrimination power as it has been claimed, we further propose an alternative solution to the formulation using bi-objective linear programming. It is shown that the proposed bi-objective multiple criteria DEA(BiO-MCDEA) performs better than the GPDEA models in the aspects of discrimination power and weight dispersion, as well as requiring less computational codes. An application of energy dependency among 26 European Union member countries is further used to describe the efficacy of our approach.