A novel robust network data envelopment analysis approach for performance assessment of mutual funds under uncertainty
提出鲁棒网络数据包络分析方法，结合非合作博弈与鲁棒优化，评估15只共同基金在财务数据不确定性下的绩效，发现该方法比确定性模型更具区分力。
Abstract Mutual fund (MF) is one of the applicable and popular tools in investment market. The aim of this paper is to propose an approach for performance evaluation of mutual fund by considering internal structure and financial data uncertainty. To reach this goal, the robust network data envelopment analysis (RNDEA) is presented for extended two-stage structure. In the RNDEA method, leader–follower (non-cooperative game) and robust optimization approaches are applied in order to modeling network data envelopment analysis (NDEA) and dealing with uncertainty, respectively. The proposed RNDEA approach is implemented for performance assessment of 15 mutual funds. Illustrative results show that presented method is applicable and effective for performance evaluation and ranking of MFs in the presence of uncertain data. Also, the results reveal that the discriminatory power of robust NDEA approach is more than the discriminatory power of deterministic NDEA models.