摘要
传统的CVaR条件风险价值组合投资模型能够很好的度量市场风险，但是容易在决策的过程中产生极端的投资权重，对CVaR模型增加一般范数约束后可以解决极端投资权重的问题，但却忽略了金融市场上常见的板块联动效应。基于上述原因，文章在传统的CVaR模型的基础上，施加Adaptive Group LASSO惩罚，构建了一种基于Adaptive Group LASSO的CVaR高维组合投资模型，通过Adaptive Group LASSO分位数回归求解算法，实现了在消除极端投资头寸的同时达到金融资产组水平上变量稀疏化的目的。最后，蒙特卡洛模拟与实证研究均发现，与传统的CVaR组合投资模型以及带有LAS—SO约束的CVaR组合投资模型相比，基于Adaptive Group LASSO的CVaR模型能够更好的考虑板块联动效应，并在行业组水平上选择相应的金融资产。
Although it is capable for traditional portfolio model with CVaR to measure the risk of monetary market, extreme asset weighting may be produced. Enforcing norm constraint on traditional portfolio model with CVaR could solve this problem, while relative effects of return volatility among industry parts are overlooked. Therefore, in the article portfolio model with CVaR and adaptive group LASSO was established to remove the possibility that extreme asset weighting may occur. Through the Adaptive Group LASSO quantile regression algorithm, it implements the investment in eliminating extreme positions at the same time to achieve financial asset Group level variables sparse purpose. Finally, based on Monte - Carlo simulation and empirical analysis, the model established in the article has better fitting results compared with traditional portfolio model with CVaR and the model with LASSO.
作者
张杰
Zhang Jie(School of Statistics and Mathematics,Zhongnan University of Economics and Law,Wuhan 430073,China)
出处
《中南财经政法大学研究生学报》
2018年第1期50-57,共8页
Journal of the Postgraduate of Zhongnan University of Economics and Law
