DYNAMIC HEDGE FUND STYLE ANALYSIS WITH ERRORS‐IN‐VARIABLES
针对对冲基金风格分析中时变暴露和变量误差问题，提出用卡尔曼滤波选择基准并修正误差，从而更精确识别收益来源。
Abstract We revisit the traditional return‐based style analysis in the presence of time‐varying exposures and errors‐in‐variables (EIV). We apply a benchmark selection algorithm using the Kalman filter and compute the estimated EIV of the selected benchmarks. We adjust them by subtracting their EIV from the initial return series to obtain an estimate of the true uncontaminated benchmarks. Finally, we run the Kalman filter on these adjusted regressors. Analyzing EDHEC alternative index styles, we show that this technique improves the factor loadings and allows more precise identification of the return sources of the considered hedge fund strategy.