不同分布下非对称GARCH模型波动率预测评价  

Volatility Evaluation on Asymmetric GARCH Model under Different Distributions

作　　者：茹正亮[1] 杨芝艳[1] 朱文刚[1] 高安力[1] 

机构地区：[1]南京工程学院基础部,南京211167

出　　处：《西南师范大学学报（自然科学版）》2012年第11期19-23,共5页Journal of Southwest China Normal University(Natural Science Edition)

基　　金：南京工程学院校级科研基金项目资助(QKJB2011022)

摘　　要：以损失函数为评价标准,研究不同分布(正态分布、T分布、广义误差分布、偏态T分布)下非对称GARCH模型在上证综合指数波动率的预测能力并进行比较.结果表明,无论样本内还是样本外,非对称GARCH模型均能很好地预测上证综合指数的波动率,其中偏态T分布下TGARCH模型能更加准确地描述收益率分布的尖峰厚尾及非对称特征,预测能力最强.Based on the loss function criterion,the volatility forecasting ability of asymmetric GARCH model under different distributions（normal distribution,T distribution,generalized error distribution,and Skewed T distribution） in the Shanghai composite index has been studied and compared in this paper.The results show that asymmetric GARCH model can predicts the Shanghai composite index volatility well,either the sample or out-of-samples.It has been found that the TGARCH model with Skewed T distribution has the strongest predictive power,and best accuracy to describe the kurtosis and asymmetry characteristics of the distribution of returns.

关 键 词：损失函数 偏态T分布 TGARCH模型 波动率 

分 类 号：O211.6[理学—概率论与数理统计]