基于VaR风险测度的投资组合优化模型及应用

Optimal Portfolio Model Based on VaR and Its Application

以VaR作为投资组合风险的衡量尺度 ,在马柯维茨框架下建立均值 -VaR投资组合优化模型 ,并采用蒙特卡罗模拟与遗传算法相结合的方法求解该模型 .通过该模型在中国股市的实证研究 ,从资产收益率分布的假设与VaR置信水平的假设两方面对投资决策的影响进行了讨论 ,发现如果资产收益率分布的尾部越厚、VaR置信水平越高 。

With VaR as a measure of investment combination, the 'M ean-VaR' optimal portfolio model was established by using Markowitz's Portfolio Theory. Furthermore, Mont Carlo simulation method as well as the Genetic Algorit hm was designed for solving this model. Following, through the study on China st o ck market analysis was given to examine the proposed method, some valuable resul t s that if the fatter the tail of the distribution is,or the higher VaR confidenc e level is, then the more conservative the portfolio decision is can be obta ined by discussing the effect on investment from the hypothesis of between the d istribution of capital asset rate and the VaR confidence level.