沪深300股指期货极差波动率的分布特征和长记忆性分析——基于频域的检验方法

Distributional Property of Range Volatility of Index Future and Its Long Memory Analysis

当前对于沪深300股指期货的研究多集中于期货市场的价格发现功能,对于极差波动率方面还未涉及。以沪深300股指期货近5年的日数据为样本,分析沪深300股指期货极差波动率的相应统计特征。采用极差波动率建模方法,对沪深300股指期货的波动率进行建模,分析其分布性质。基于频域的检验方法,检验期货极差波动率是否为真实长记忆过程,利用GPH和局部Whittle方法对极差波动率的记忆参数进行估计。结果发现,对数极差波动率的偏度和峰度为自相关系数呈缓慢衰减,显示出长记忆性,期货极差波动率为真实长记忆过程,且参数值接近于典型值0.4,以此为依据进行波动率预测工作。

Current research focuses mostly on？ price discovery function of Hushen 300 index future and rarely involves its range volatility.Based on daily data of hushen 300 index future in recent five years, this paper models the volatility of hushen 300 index future by range volatility and analysis its distributional property. Testing whether range volatility is a true long memory process by a test based on frequency and using GPH and local Whittle to estimate memory parameter of range volatility. The study shows that skewness and kurtosis of range volatility are 0.193 and 2.919, and its autocorrelation decays slow,ly and displays long-memory effects; range volatility is true long memory process by frequency test under different band parameter; memory parameter of range volatility approxi-mates typical value 0.4. On this basis it can be used to forecast volatility.