Mutual Fund Performance Dynamic Evaluation Using Data Envelopment Windows Analysis

In this paper, we mainly present data envelopment analysis (DEA) based method for evaluating portfolio performance in two aspects, (a) To reflect the pervasive fat tails and asymmetry in return distributions of mutual funds, we introduce risk measure CVaR into DEA indices for measuring relative performance of portfolios more objectively, (b) We creatively treat the same funds during different time periods as different decision making units (DMUs) to fairly observe the performance variation. Our empirical results show that our model can better evaluate mutual funds' overall performance variation during a long time period.