中国股市波动的异方差模型及其SPA检验

被引:21
作者
魏宇
机构
[1] 西南交通大学经济管理学院
基金
国家杰出青年科学基金;
关键词
异方差; 实现波动率; GARCH模型; 随机波动模型; SPA检验;
D O I
暂无
中图分类号
F832.51 []; F224 [经济数学方法];
学科分类号
1201 ; 020204 ; 0701 ; 070104 ;
摘要
以中国股票市场最具代表性的股价指数-上证综指的高频(High-frequency)数据样本为例,实证计算了以GARCH族模型和随机波动(Stochastic volatility)模型为代表的不同异方差模型对中国股市波动率的预测,并进一步运用SPA(Superior predictive ability)检验法,实证检验了不同异方差模型对中国股市波动的刻画能力和预测精度问题.实证结果显示,就中国股市而言,随机波动(Stochastic volatility)模型是预测精度最高的异方差模型,但在某些损失函数标准下,EGARCH模型也具有良好的波动预测表现.
引用
收藏
页码:27 / 35
页数:9
相关论文
共 8 条
[1]  
A forecast comparison of volatility models:does anything beat a GARCH(1,1)?. Hansen P R,Lunde A. Journal of AppliedEconometrics . 2005
[2]  
Consistent ranking of volatility models. Hansen P R,Lunde A. Journal of Econometrics . 2006
[3]  
Autoregressive conditional heteroskedasticity with estimates of the variance of the United Kingdom inflation. Engle R F. Econometrica . 1982
[4]  
Estimation of stochastic volatility models via Monte Carlo maximum likelihood. Sandmann G,Koopman S J. Journal of Econometrics . 1988
[5]  
Correcting the errors:volatility forecast evaluation using high frequency data and realizedvolatilities. Andersen T G,Bollerslev T,Meddahi N. Econometrica . 2005
[6]  
Answering the skeptics:yes,standard volatility models do provide accurate forecasts. Andersen T G,Bollerslev T. International Economic Journal . 1998
[7]  
Generalized autoregressive conditional heteroskedasticity. Bollerslev T. Journal of Econometrics . 1986
[8]  
A reality check for data snooping. White H. Econometrica . 2000