期货套期保值模型选择:基于模型(误设)风险与估计风险视角  

The Model Selection of Futures Hedging:Model-Misspecification Risk and Estimation Risk?

作　　者：付剑茹[1] 袁倩莹 张伟 FU Jianru;YUAN Qianying;ZHANG Wei(School of Financial,Jiangxi Normal University,Nanchang,Jiangxi 330022,China)

机构地区：[1]江西师范大学财政金融学院,江西南昌330022

出　　处：《经济数学》2020年第4期38-46,共9页Journal of Quantitative Economics

基　　金：国家自然科学基金资助项目(71661014,71261010)。

摘　　要：在市场环境发生变化时,针对复杂模型对套期保值的影响,从两个维度对样本检验来判断样本期是否存在市场环境突变,选取动态VAR-DCC-GARCH模型为主研模型,静态OLS、VAR、EC-VAR模型为基础模型,比较两类模型环境突变前后的套期保值表现.实证结果显示:样本内,静态模型和动态模型的套期保值表现并没有明显的差异.样本外,所有模型的套期保值效率均会下降.模型越复杂,效率下降幅度越大,其中动态模型的套期保值效率下降最大,样本外表现最差.表明复杂模型包含更多噪音,市场环境发生变化时,其表现会劣于简单模型.When the market changes,for the impact of complex models on hedging,this article checks the sample from two dimensions to determine whether there is a sudden change in the market during the sample period.The dynamic VAR-DCC-GARCH model is selected as the main model,and the static OLS,VAR and EC-VAR models are the basic models.The hedging performance of the two types of models between the two stages is compared.The empirical results show that there is no significant difference in the hedging performance between the static model and the dynamic model when in the in-sample stage.The out-of-sample hedging efficiency of all models will decrease.The more complex the model,the greater the decrease in efficiency.The hedging efficiency of the dynamic model decreases the most,and the out-of-sample performance is the worst,which show that complex models contain more noise.When the market changes,its performance will be inferior to the simple model.

关 键 词：股指期货 套期保值 随机过程 模型选择 模型(误设)风险 模型估计风险 

分 类 号：F830.9[经济管理—金融学]