Improving envelopment in data envelopment analysis

R. Allen, E. Thanassoulis*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


Data envelopment analysis defines the relative efficiency of a decision making unit (DMU) as the ratio of the sum of its weighted outputs to the sum of its weighted inputs allowing the DMUs to freely allocate weights to their inputs/outputs. However, this measure may not reflect a DMU's true efficiency as some inputs/outputs may not contribute reasonably to the efficiency measure. Traditionally, to overcome this problem weights restrictions have been imposed. This paper offers a new approach to this problem where DMUs operate a constant returns to scale technology in a single input multi-output context. The approach is based on introducing unobserved DMUs, created by adjusting the output levels of certain observed relatively efficient DMUs, reflecting a combination of technical information of feasible production levels and the DM's value judgments. Its main advantage is that the information conveyed by the DM is local, with reference to a specific observed DMU. The approach is illustrated on a real life application. © 2003 Elsevier B.V. All rights reserved.

Original languageEnglish
Pages (from-to)363-379
Number of pages17
JournalEuropean Journal of Operational Research
Issue number2
Publication statusPublished - 16 Apr 2004


  • data envelopment analysis
  • linear programming applications
  • performance management
  • productivity analysis
  • value judgments


Dive into the research topics of 'Improving envelopment in data envelopment analysis'. Together they form a unique fingerprint.

Cite this