In this paper, one-stage and two-stage nonlinear programming problems are investigated in order to evaluate the efficiency of two types of network data envelopment analysis model. | A two-stage method for assessing the efficiency of the three-stage series network data envelopment analysis model with two feedback Decision Science Letters 8 2019 339 352 Contents lists available at GrowingScience Decision Science Letters homepage dsl A two-stage method for assessing the efficiency of the three-stage series network data envelopment analysis model with two feedback Hamidreza Ghomia Morteza Rahmania b and Morteza Khakzar Bafruei a b aIndustrial engineering department Research institute of Technology development ACECR Tehran Iran bUniversity of Science and Culture Tehran Iran CHRONICLE ABSTRACT Article history Data envelopment analysis models play an important role in decision making. In this paper one- Received June 9 2018 stage and two-stage nonlinear programming problems are investigated in order to evaluate the Received in revised format efficiency of two types of network data envelopment analysis model. The first type of network August 10 2018 data envelopment analysis model has a series structure with three stages and a feedback between Accepted September 29 2018 Available online the last step and the middle step the second model has a three-stage series structure with two September 29 2018 feedback between the final step and the first step and the middle step. By examining the overall Keywords efficiency of the models based on the one-stage programming problem a two-stage programming NDEA problem is also applied in order to evaluate the efficiency of each step. In order to solve one- Three-stage series structure stage nonlinear programming problems and two-stage linear and nonlinear programming Non-linear programming problem problems derived from modeling a linearization method based on coordinate transformation Efficiency calculation and constant assumption and gradual growth of some variables is presented. In the last section Linearization the proposed methods have been discussed using some numerical examples. 2018 .