基于已实现波动率的ARFIMA模型在股指期货高频数据中的实证研究  

An Empirical Study on ARFIMA Model Based on Realized Volatility in High Frequency Data of Stock Index Futures

作　　者：杨若一 胡冰霜[2] Yang Ruoyi;Hu Bingchen(Chengdu Yi Tai Tai Li Asset Management Co., Ltd., Chengdu, Sichuan Province, 610000;Department of Sociology and Psychology, Sichuan University, Chengdu 610000, China)

机构地区：[1]成都依摩泰立资产管理有限公司,四川成都610000 [2]四川大学社会学与心理学系,四川成都610000

出　　处：《中国国际财经（中英文版）》2017年第3期38-42,共5页China International Business

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%.

关 键 词：ARFtMA模型 高频数据 已实现波动率 预测 

分 类 号：F239.41[经济管理—会计学]