A Bounded Additive Model for Efficiency Evaluation in Two-Stage Production Systems With Negative Data

Data Envelopment Analysis (DEA) is a method for assessing the efficiency of Decision Making Units (DMUs). Traditional DEA models do not examine the potential differences between two stages caused by intermediate operations. As a result, DEA has been extended to evaluate the efficiency of two-stage processes. In these processes, all outputs of the first stage are intermediate operations that comprise the inputs of the second stage. The input data in real-world applications may have negative values. In this study, considering the importance of network production processes, we deal with the efficiency evaluation of two-stage production units with negative data. Also, we extend CRS (constant returns to scale) bounded additive model for the efficiency evaluation of the two-stage units in the presence of negative data. For illustration, we evaluate the efficiency and ranking of 36 airlines by applying the new model.