基于GARCH-EVT模型VaR法的开放式基金风险测度研究  被引量:2

Research on Open Fund Risk Measurement Based on VaR Method and GARCH-EVT Model

在线阅读下载全文

作  者:程建华[1] 丁慧敏 Cheng Jian-hua;Ding Hui-min(Anhui University,Hefei Anhui 230601,China)

机构地区:[1]安徽大学,安徽合肥230601

出  处:《铜陵学院学报》2018年第4期30-36,共7页Journal of Tongling University

摘  要:VaR(Value at Risk)法是一种能够全面测量复杂证券组合的市场风险的方法,在风险测量和管理中具有明确的理论指导意义,在金融市场中极端事件时有发生,VaR度量极端事件下的金融市场风险误差较大,而极值理论则为测量极端市场条件下的风险提供了一种新思路。根据金融时间序列往往具有高峰厚尾以及波动集聚特征,传统的VaR估计通常基于GARCH模型,文章针对极端情况下的基金市场风险,将基于GARCH模型的VaR法与基于EVT(Extreme value theory)的VaR法相结合,以契约型开放式基金易方达50指数日指数条件损失作为研究目标,利用GARCH-EVT模型,对样本基金的市场风险进行估计,并通过Kupiec失败频率检验方法检验模型的准确性。结果表明,GARCH-EVT模型的VaR估计精度优于GARCH模型,故GARCH-EVT模型更能精准度量基金的市场风险。The VaR(Value at Risk) method is a comprehensive method to measure the market risk of complex portfolio. It has a clear theoretical guiding significance in risk measurement and management, but the extreme events occur in the financial market, the error of financial market risk under extreme events measured by VaR is large, and the extreme value theory provides a new method to measure the risk in extreme market conditions. According to the characteristics of financial time series such as peak thick tail and volatility agglomeration, traditional VaR estimation is usually based on GARCH model. In this paper, we combine the VaR method based on GARCH model with the VaR method based on EVT(Extreme value theory), aiming at the risk of fund market in extreme cases.The research aim is to study the daily index loss of Easy Fonda-50 index of contractual open-end fund.In this paper, GARCH-EVT model is used to estimate the market risk of sample funds, and Kupiec failure frequency test method is used to verify the accuracy of the model. The results show that the VaR estimation accuracy of GARCH-EVT model is better than that of GARCH model, so GARCH-EVT model can accurately measure the market risk of funds.

关 键 词:基金风险度量 GARCH模型 极值理论 Kupiec回测 

分 类 号:F830.9[经济管理—金融学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象