Fuzzy stochastic input-oriented primal data envelopment analysis models with application to insurance industry. (2016)

• Record Type: Journal Article
• Authors: Nasseri, Seyed Hadi; Ebrahimnejad, Ali; Gholami, Omid
• Is Part Of: International journal of applied decision sciences. Volume 9:Number 3(2016)
• Page Start: 259
• Page End: 282
• Publication Date: 2016
• Subjects: data envelopment analysis -- fuzzy DEA -- fuzzy random variables -- normal distribution -- efficiency scores -- fuzzy logic -- insurance industry -- decision making units -- DMUs -- stochastic variables; Decision making -- Periodicals; Management science -- Periodicals; 658.403005
• Languages: English
• ISSNs: 1755-8077

Abstract

Data envelopment analysis (DEA) is a widely used technique for measuring the relative efficiencies of decision making units (DMUs) with multiple inputs and multiple outputs. However, in real-world problems, the observed values of the input and output data are often vague or random. Indeed, decision makers (DMs) may encounter a hybrid uncertain environment where fuzziness and randomness coexist in a problem. This paper proposes a normal distribution with fuzzy components to deal with fuzziness and randomness of input and output data. The proposed normal distribution introduces a class of fuzzy random variables. We propose a DEA model problems characterised by fuzzy stochastic variables. Unlike the existing approaches, the proposed fuzzy stochastic DEA model is transformed into a deterministic model with linear constraints. A case study in the insurance industry is presented to exhibit the efficacy and the applicability of the proposed model.