Mutual Funds’ Conditional Performance Free of Data Snooping Bias
提出一种名为fFDR+的方法，利用基金特征和更新信息评估共同基金的条件业绩，同时纠正数据窥探偏差，模拟显示该方法比传统方法更有效，选出的基金组合表现更优。
Abstract We introduce a test to assess mutual funds’ “conditional” performance that is based on updated information and corrects data snooping bias. Our method, named the functional false discovery rate “plus” ( $ {\mathrm{fFDR}}^{+} $ ), incorporates fund characteristics in estimating fund performance free of data snooping bias. Simulations suggest that the $ {\mathrm{fFDR}}^{+} $ controls well the ratio of false discoveries and gains considerable power over prior methods that do not account for extra information. Portfolios of funds selected by the $ {\mathrm{fFDR}}^{+} $ outperform other tests not accounting for information updating, highlighting the importance of evaluating mutual funds from a conditional perspective.