Reduction of estimation error impact in the risk parity strategies
研究估计误差对风险平价策略的影响，发现风险贡献对估计误差高度敏感，尤其当组合包含低相关性因子时。提出新算法降低这种敏感性，实证表明新算法在样本外风险贡献上优于其他方法。
We consider the risk parity strategy in the presence of estimation errors. We show that risk contributions from constituents of this portfolio can be considerably sensitive to estimation errors in the sense that risk contributions are highly uneven on an ex post basis. In particular, we demonstrate that the sensitivity becomes exaggerated if Fama-French factors constitute the portfolio because of their characteristic of having low pairwise correlations. Our work demonstrates that the instability of the out-of-sample risk contributions is associated with a local property with statistical significance near to the constructed portfolio. Based on this observation, we propose a new algorithm for the risk parity strategy to mitigate the sensitivity of the optimized portfolio's out-of-sample risk contributions from estimation errors. Through empirical study, we find that the portfolio constructed by the proposed algorithm consistently outperforms its competitors in terms of the out-of-sample risk contributions.