Modelling undesirable outputs in multiple objective data envelopment analysis

Mahdi Mahdiloo, Abdol Hossein Jafarzadeh, Reza Farzipoor Saen*, Yong Wu, John Rice

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


Recent empirical and conceptual work in data envelopment analysis (DEA) have emphasised its potential importance in highlighting the environmental performance of economic entities. Initial work in this emerging research area has focused on the separation of output factors into desirable and undesirable ones. In this paper, we describe recent developments in the modelling undesirable outputs. In particular, the modelling of undesirable outputs in the range adjusted measure (RAM) is investigated. We discuss some of the difficulties of RAM in assessing the environmental efficiency of decision-making units (DMUs) and develop a multiple objective DEA model to overcome these difficulties. The proposed multiple objective model is solved as a linear programming and its applicability as a mechanism for assessing environmental efficiency is demonstrated by evaluating the technical, ecological and process environmental quality efficiency scores of China’s provinces.

Original languageEnglish
Pages (from-to)1903-1919
Number of pages17
JournalJournal of the Operational Research Society
Issue number12
Publication statusPublished - Dec 2 2018


  • Data envelopment analysis
  • ecological efficiency
  • multiple objective
  • process environmental quality efficiency
  • undesirable outputs

ASJC Scopus subject areas

  • Management Information Systems
  • Strategy and Management
  • Management Science and Operations Research
  • Marketing

Cite this