Roza Azizi - Islamic Azad University, Karaj Branch, Department of Mathematics, Karaj, Iran
Reza Kazemi Matin - Islamic Azad University, Karaj Branch, Department of Mathematics, Karaj, Iran

Data envelopment analysis (DEA) is a non-parametric approach for performance analysis of decision making units (DMUs) which uses a set of inputs to produce a set of outputs without the need to consider internal operations of each unit. In recent years, there have been various studies dealt with two-stage production systems, i.e. systems which consume some inputs in their first stage to produce some intermediate outputs which are used as the inputs of the second stage in producing final outputs. One of these researches done by Kao and Hwang (2008) gives a decomposition of system efficiency score based on the efficiency of its sub-processes in the case of constant returns to scale (CRS) technology. This paper presents an extension of this approach for the technologies with variable returns to scale (VRS) and explains the results

Data envelopment analysis; two-stage systems; constant returns to scale; variable returns to scale