Title: Fuzzy free disposal hull models under possibility and credibility measures


Author: Rashed Khanjani Shiraz; Madjid Tavana; Khalil Paryab


School of Mathematics, Iran University of Science and Technology, 1684613114 Tehran, Iran
Business Systems and Analytics Department, La Salle University, Philadelphia, PA 19141, USA
School of Mathematics, Iran University of Science and Technology, 1684613114 Tehran, Iran


Journal: Int. J. of Data Analysis Techniques and Strategies, 2014 Vol.6, No.3, pp.286 - 306


Abstract: The free disposal hull (FDH) models are used as an alternative to data envelopment analysis (DEA) models for performance measurement and efficiency assessment. The conventional FDH models are used to evaluate the performance of a set of firms or decision-making units (DMUs) using deterministic input and output data. However, the input and output data in the real-life performance evaluation problems are often imprecise and ambiguous. The impreciseness and ambiguity associated with the input and output data in FDH can be represented with fuzzy variables. In this paper, the concept of chance-constrained programming is used to develop FDH models with various returns to scale assumptions, including variable returns to scale (VRS), variable non-increasing returns to scale (NIRS), variable non-decreasing returns to scale (NDRS), and constant returns to scale (CRS), for efficient DMUs with fuzzy data. We propose two fuzzy FDH models with respect to possibility and expected value (credibility approach) constraints. Finally, a numerical example is presented to demonstrate the efficacy of the proposed procedures and algorithms.


Keywords: data envelopment analysis; DEA; free disposal hull; FDH models; credibility measures; possibility measures; fuzzy sets; fuzzy logic; performance measurement; efficiency assessment; chance-constrained programming; decision making units; DMUs; DMU efficiency; modelling.


DOI: http://dx.doi.org/10.1504/IJDATS.2014.063072


Available online 25 Jun 2014



Editors Full Text AccessAccess for SubscribersPurchase this articleComment on this article