Stochastic Data Envelopment Analysis in the Presence of Undesirable Outputs

In contrast to traditional efficiency analysis models in the field of data envelopment analysis (DEA) with undesirable outputs, this paper proposes efficiency models with the joint use of weak and managerial disposability assumptions. First, we develop a deterministic efficiency analysis model to deal with undesirable outputs in a production process. Due to the importance of data variability and uncertainty, the technical efficiency analysis is sensitive to these variations. Using chance-constrained programming theory, we extend our proposed deterministic model to a stochastic production system. To demonstrate the real-world applicability of our proposed models, we employ an empirical application based on actual Iranian gas distribution company data. Although this empirical application is illustrative, our proposed scheme could be used to evaluate the relative efficiency of many real-life production units whose underlying production systems are frequently stochastic.