Robust optimization and its duality in data envelopment analysis

doi:10.1016/j.omega.2021.102583

Return

Robust optimization and its duality in data envelopment analysis

2022-04-01

PRE

Mehdi Toloo *

Emmanuel Kwasi Mensah

Maziar Salahi

DOI：10.1016/j.omega.2021.102583

Original

Original request for help

Save

Abstract

En 中文

Robust Data Envelopment Analysis (RDEA) is a DEA-based conservative approach used for modeling uncertainties in the input and output data of Decision-Making Units (DMUs) to guarantee stable and reliable performance evaluation. The RDEA models proposed in the literature apply robust optimization techniques to the linear and conventional DEA models which lead to the difficulty of obtaining a robust efficient DMU. To overcome this difficulty, this paper tackles uncertainty in DMUs from the original fractional DEA model. We propose a robust fractional DEA (RFDEA) model in both input and output orientation which enables us to overcome the deficiency of existing RDEA models. The linearized models of the fractional DEA are further used to establish duality relations from a pessimistic and optimistic view of the data. We show that the primal worst of the multiplier model is equivalent to the dual best of the envelopment model. Furthermore, we show that the robust efficiency in the input-and output-oriented DEA models are still equivalent in the new approach which is not the case in conventional RDEA models. We finally present a study of the largest airports in Europe to illustrate the efficacy of the proposed models. The proposed RDEA is found to provide an effective management evaluation strategy under uncertain environments.(c) 2021 Elsevier Ltd. All rights reserved.

Keywords:

Data envelopment analysis

Robust DEA

Duality in Robust DEA

Uncertainty in efficiency measurement

European airports