典型事实约束下的上海燃油期货市场动态VaR测度研究

发布时间：2018-07-07 20:28

本文选题：燃油期货 + 动态风险测度　；参考：《中国管理科学》2013年02期

【摘要】：期货交易的高杠杆率意味着期货市场的高风险特征,而能源市场因其特殊的战略意义一直以来备受关注,因而对能源期货市场的风险测度对投资者和监管者都极其重要。本文对上海燃油期货构建了四个反映不同交割期限的连续价格序列,基于不同的金融市场典型事实分别运用GARCH、GJR、FIGARCH三个模型对波动率建模,并假设条件收益分别服从正态、学生t、有偏学生t(skst)分布进行动态风险价值(VaR)测度,然后运用严格的似然比(LR)检验和动态分位数回归(DQR)检验对风险测度的可靠性进行后验分析(Backtesting),尝试从中提取出在风险管理中最有应用价值的典型事实。研究发现:(1)基于skst分布的波动模型的动态风险测度准确性明显优于其他分布下的相同模型;(2)基于杠杆效应的GJR模型和基于长记忆性的FIGARCH模型并没有表现出比普通GARCH模型更高的精度;(3)远期合约的市场平均收益更高,风险测度比近期合约更准确。
[Abstract]:The high leverage ratio of futures trading means the high risk characteristics of the futures market, and the energy market has been paid close attention to because of its special strategic significance, so the risk measurement of the energy futures market is extremely important to investors and regulators. In this paper, four successive price sequences reflecting different delivery periods are constructed for Shanghai fuel futures. Based on the typical facts of different financial markets, volatility models are established using GARCHN GJR FIGARCH models, and the conditional returns are assumed to be normal respectively. Student t, biased student t (skst) distribution to measure the value of dynamic risk (VaR), Then we use the strict likelihood ratio (LR) test and the dynamic quantile regression (DQR) test to analyze the reliability of risk measurement by Backtesting, and try to extract the typical facts that are most valuable in risk management. The results show that: (1) the dynamic risk measurement accuracy of the volatility model based on skst distribution is obviously better than that of the same model under other distributions; (2) the GJR model based on leverage effect and the Fig model based on long memory have not shown more accuracy than the common model. The GARCH model has higher accuracy. (3) the market average return of forward contracts is higher. Risk measurement is more accurate than recent contracts.
【作者单位】：成都理工大学商学院;西南交通大学经济管理学院;
【基金】：国家自然科学基金(71071131,71171025,71271227) 国家社会科学基金(12BGL024) 教育部人文社科研究项目(10YJCZH086) 成都理工大学金融与投资优秀科研创新团队培育资助项目(KYTD201303)
【分类号】：F224;F724.5;F426.22

【参考文献】