Some properties of Pareto efficiency under the framework of data envelopment analysis
- 1 September 1995
- journal article
- research article
- Published by Informa UK Limited in International Journal of Systems Science
- Vol. 26 (9), 1549-1558
- https://doi.org/10.1080/00207729508929118
Abstract
Data envelopment analysis (DEA) has been widely applied to measure the Pareto efficiency of multiple-input and multiple-output decision making units (DMUs). In this paper it is shown that under linear production frontiers DMU efficiency is a weighted arithmetic mean of the efficiencies of the outputs; whereas under loglinear production frontiers DMU efficiency is a weighted geometric mean of the output efficiencies. Furthermore, DMU efficiency can be decomposed with respect to input factors as well, and some results are derived. As a consequence, a modified DEA model is devised, whereby the efficiency of each output (or input) in addition to DMU efficiency is able to be measured in one linear programming solution.Keywords
This publication has 13 references indexed in Scilit:
- A model for measuring productive efficiencyJournal of the Chinese Institute of Engineers, 1986
- Piecewise Loglinear Estimation of Efficient Production SurfacesManagement Science, 1986
- Some Models for Estimating Technical and Scale Inefficiencies in Data Envelopment AnalysisManagement Science, 1984
- Measuring Productive Efficiency: An Application to Illinois Strip MinesManagement Science, 1984
- The non-archimedean CCR ratio for efficiency analysis: A rejoinder to Boyd and FäreEuropean Journal of Operational Research, 1984
- A multiplicative model for efficiency analysisSocio-Economic Planning Sciences, 1982
- A survey of frontier production functions and of their relationship to efficiency measurementJournal of Econometrics, 1980
- Measuring the efficiency of decision making unitsEuropean Journal of Operational Research, 1978
- Measuring the technical efficiency of productionJournal of Economic Theory, 1978
- The Measurement of Productive EfficiencyJournal of the Royal Statistical Society. Series A (General), 1957