Computation of Output Losses due to Congestion in Data Envelopment Analysis

Data Envelopment Analysis (DEA) is an approach for evaluating performances of Decision Making Units (DMUs). The performances of DMUs are affected by the amount of sources that DMUs used. Usually increases in inputs cause increases in outputs. However, there are situations where increases in one or more inputs generate a reduction in one or more outputs. In such situations there is congestion in inputs or production process. In this study, we review two approaches that are available in the DEA literature for evaluating congestion. Afterwards, we focus on output losses due to congestion, and a model is introduced to compute output reduction. Then, the mentioned models are applied on an empirical example and the results are presented and interpreted.