论文部分内容阅读
金融实践中,金融资产回报不仅具有厚尾性、波动的异方差性两大特点,而且其波动表现出明显的长期记忆性。本文利用FIGARCH模型处理波动异方差性和长期记忆性、EVT-POT方法捕捉回报分布厚尾的优势,提出了能反映厚尾性、异方差性和长期记忆性的金融风险度量模型——基于EVT-POT-FIGARCH的动态VaR模型,并用中国股票市场的沪深300指数和上证综合指数的每日收盘价进行实证分析。结果表明,模型能较好地处理这两个指数回报序列的三大特点,更准确地度量其VaR风险。
In financial practice, the return of financial assets not only has the characteristics of thick-tailed, fluctuating heteroscedasticity, but also its volatility shows obvious long-term memory. In this paper, we use the FIGARCH model to deal with the volatility heterogeneity and long-term memory, and the EVT-POT method to capture the advantage of the thick-tailed return distribution. We propose a financial risk measurement model that can reflect thick tail, heteroscedasticity and long- -POT-FIGARCH dynamic VaR model, and empirical analysis of the daily closing price of the Shanghai and Shenzhen 300 Index and the Shanghai Composite Index of China’s stock market. The results show that the model can better handle the three characteristics of these two index return sequences and measure the VaR risk more accurately.