Exact and stochastic methods for robustness analysis in the context of Imprecise Data Envelopment Analysis

Abstract We consider the problem of measuring efficiency decision-making units with a ratio-based model. In this perspective, we introduce framework for robustness analysis that admits both interval and ordinal performances on inputs outputs. The proposed methodology exploits uncertainty related to imprecise data all feasible input/output weight vectors delimited through linear constraints. offer methods verifying three types outcomes: scores, preference relations, ranks. On one hand, formulate mathematical programming models compute extreme, necessary, possible results. other incorporate stochastic driven by Monte Carlo simulations derive probability distribution different outcomes. is implemented in R made available open-source software. Its use illustrated two case studies concerning Chinese ports or industrial robots.