基于GARCH类模型沪深300股指期货波动率预测研究  

A Study on Volatility Prediction of Shanghai and Shenzhen 300 Stock Index Futures Based on GARCH Models

作　　者：沈慈慈 王伟杰 侯为波[1] SHEN Cici;WANG Weijie;HOU Weibo(School of Mathematical Sciences,Huaibei Normal University,235000,Huaibei,Anhui,China;School of Education,Huaibei Institute of Technology,235000,Huaibei,Anhui,China)

机构地区：[1]淮北师范大学数学科学学院,安徽淮北235000 [2]淮北理工学院教育学院,安徽淮北235000

出　　处：《淮北师范大学学报（自然科学版）》2022年第4期23-29,共7页Journal of Huaibei Normal University：Natural Sciences

基　　金：安徽高校自然科学研究项目(KJ2021A1242)。

摘　　要：文章以沪深300股指期货为研究对象,对GARCH类模型的样本内、外预测表现进行评价.选取日收盘价数据,对其日对数收益率序列进行基本的统计分析,验证序列具有ARCH效应.通过泊松拟合优度检验模型的标准化残差假定分布,选取最优的分布建立GARCH类模型.以已实现波动率作为波动率预测的评价标准,采用M-Z回归和损失函数对预测效果进行检验.结果表明,GED分布假设下的GARCH(1,1)模型是预测沪深300股指期货收益波动率最强的模型.The article evaluates the in-sample and out-of-sample forecasting performance of GARCH-type models for the CSI 300 stock index futures.The daily closing price data were selected and the daily log return series were subjected to basic statistical analysis to verify the ARCH effect of the series.The distribution of the standardized residuals of the model is tested by Poisson goodness of fit,and the optimal distribution is selected to build the GARCH-type model.Using realized volatility as the evaluation criterion for volatility forecasting,M-Z regression and loss function are used to test the forecasting effects.The results show that the GARCH(1,1)model with GED distribution assumptions is the strongest model for forecasting the volatility of CSI 300 stock index futures returns.

关 键 词：股指期货 GARCH 已实现波动率 预测能力评价 

分 类 号：F830.9[经济管理—金融学]