MC-GARCH模型在互联网金融风险度量中的实证研究

针对互联网金融风险测度问题,提出了MonteCarlo模拟法。首先,选取中证互联网金融指数作为研究对象,并对数据进行基本的统计分析,得出中证互联网金融指数对数收益率具有尖峰厚尾性和异方差性的特点,建立GARCH模型,对序列的均值和方差进行估计;其次,基于GARCH模型计算出的均值和方差,利用MonteCarlo模拟法计算中证互联网金融指数的VaR和CVaR值;最后,对模型的准确性和精确度方面进行Kupiec返回检验。结果表明:VaR和CVaR均可作为度量互联网金融风险的工具,但VaR无论在准确性上还是精确度上都远低于CVaR,故CVaR是一种更优良的风险测度工具。

An Empirical Study of MC-GARCH Model in Internet Financial Risk Measurement

According to the problem of internet financial risk measurement,this paper proposes to measure the Internet risk measurement by Monte Carlo simulation.Firstly,the CSI Internet Financial Index is selected as the research object,and the basic statistical analysis of the data is carried out. It is concluded that the logarithmic yield of the CSI Internet Financial Index has the characteristics of sharp tail and heteroscedasticity,and the GARCH model is established.The mean and variance are estimated. Secondly,based on the mean and variance calculated by the GARCH model,the Monte Carlo simulation method is used to calculate the VaR and CVaR values of the CSI Internet Financial Index. Finally,the Kupiec return is performed on the accuracy and accuracy of the model.Tests show that both VaR and CVaR can be used as tools to measure Internet financial risk,but VaR is much better than CVaR in accuracy and accuracy,so CVaR is a better risk measurement tool.