Finding Common Weights in Two-Stage Network DEA

Subject Areas : International Journal of Data Envelopment Analysis

Mohammad Reza Mozaffari ¹ , mehrnoosh khazraei ²

1 - Department of Mathematics, Shiraz Branch, Islamic Azad University, Shiraz, Iran
2 - Department of mathematic, Shiraz branch, Islamic Azad university, Shiraz, Iran.

Received: 2017-04-07 Accepted : 2017-08-12 Published : 2017-10-01

Keywords: Data Envelopment Analysis, Ranking, Decision-making unit, Common weights, Two-stage Network,

Abstract :

In data envelopment analysis (DEA), mul-tiplier and envelopment CCR models eval-uate the decision-making units (DMUs) under optimal conditions. Therefore, the best prices are allocated to the inputs and outputs. Thus, if a given DMU was not efficient under optimal conditions, it would not be considered efficient by any other models. In the current study, using common weights in DEA, a number of de-cision-making units are evaluated under the same conditions, and a number of two-stage network DEA models are proposed within the framework of multi-objective linear programming (MOLP) for finding common weights. Furthermore, using the infinity norm, common weight sets are de-termined in two-stage network models with MOLP structures.

References:

[1] Castelli L. Pesenti R. Ukovich W. 2010.A classification of DEA models when the internal structure of the Decision Making Units is considered. Annals of Operations Reasearch, 173: 207-235.

[2] Cook WD. Liang L. Zhu J. 2010. Measuring performance of two-stage network structures by DEA: a review and future perspective. Omega, 38: 423-430.

[3] Despotis D. K. Koronakas G. Sotiros D. 2014. Composition versus decomposition in two-stage network DEA:a reverse approach. Jornal of Productivity analysis, 123:414-415