MCDM'05 - paper no. 6


Back to MCDM'05 contents

A slack based model for measuring super-efficiency in data envelopment analysis

Josef Jablonsky


Data Envelopment Analysis (DEA) models compare relative efficiency of decision making units (DMU) described by multiple inputs and outputs. In most DEA models the best DMUs reach the efficiency score of 100%. Depending on the number of units and/or inputs and outputs used in the model, the number of efficient units can be relatively high. The necessity of classification of efficient units leads to several definition of the so-called super-efficiency. In the paper A Slack Based Model for Measuring Super-Efficiency in Data Envelopment Analysis (J. Jablonsky) an original definition of super-efficiency in DEA models in proposed. The definition works directly with positive slacks of inputs and negative slack of outputs and uses standard methodology known from goal programming models. The results of a test example of the model are compared with other super-efficiency definitions (Andersen and Petersen model and SBM model). All the computational experiments are done by the original MS Excel DEA support system that uses as the optimization engine the internal MS Excel solver.

Reference index:

Josef Jablonsky, (2006), A slack based model for measuring super-efficiency in data envelopment analysis, Multiple Criteria Decision Making (1), pp. 101-112

Full text:


Scopus citations in 1 paper(s):
  1. Dar, Q. F., Padi, T. R., & Tali, A. M. (2016). Mixed input and output orientations of data envelopment analysis with linear fractional programming and least distance measures. Statistics, Optimization and Information Computing, 4(4), 326-341. doi:10.19139/soic.v4i4.225