摘要
本文利用连续的股指期货指数5分钟高频数据,基于"已实现"波动率进行实证研究,结果表明股指期货"已实现"波动率序列的分布是非正态分布且具有长记忆性,最后建立ARFIMA模型,并对波动率进行预测,预测平均误差7.20%。
This paper uses the continuous stock index futures index of 5 minutes high frequency data,based on the 'realized' volatility of the empirical study,the results show that stock index futures 'realized' volatility sequence distribution is non-normal distribution and long memory,and finally The ARFIMA model is established and the volatility is predicted to predict the average error of 7.20%.
