Developing a new super-efficiency DEA model in the presence of both zero data and stochastic data: a case study in the Iranian airline industry

Mohammad Tavassoli*, Amirali Fathi, Reza Farzipoor Saen

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

11 Citations (Scopus)

Abstract

Purpose: The purpose of this study is to propose a novel super-efficiency DEA model to appraise the relative efficiency of DMUs with zero data and stochastic data. Our model can work with both variable returns to scale (VRS) and constant returns to scale (CRS). Design/methodology/approach: This study proposes a new stochastic super-efficiency DEA (SSDEA) model to assess the performance of airlines with stochastic and zero inputs and outputs. Findings: This paper proposes a new analysis and contribution to the knowledge of efficiency assessment with stochastic super-efficiency DEA model by (1) using input saving and output surplus index for efficient DMUs to get the optimal solution; (2) obtaining efficiency scores from the proposed model that are equivalent to original stochastic super-efficiency model when feasible solutions exist. A case study is given to illustrate the applicability of our proposed model. Also, poor performance reasons are identified to improve the performance of inefficient airlines. Originality/value: For the first time, a new SSDEA model for ranking DMUs is proposed. The introduced model produces a feasible solution when dealing with zero input or output. This paper applies the input saving and output surplus concept to rectify the infeasibility problem in the stochastic DEA model.

Original languageEnglish
Pages (from-to)42-65
Number of pages24
JournalBenchmarking
Volume28
Issue number1
DOIs
Publication statusPublished - Jan 19 2021

Keywords

  • Data envelopment analysis (DEA)
  • Efficiency evaluation
  • Stochastic data
  • Super-efficiency
  • Zero data

ASJC Scopus subject areas

  • Business and International Management
  • Strategy and Management

Cite this