基于真伪跳跃的HAR类波动预测模型研究  

Research on the Forecasting Performance of the HAR-Type Model Based on True and False Jumps

作　　者：武艳华 石玉峰 WU Yanhua;SHI Yufeng(School of Statistics,Shandong University of Finance and Economics,Jinan,250014,China;Institute for Financial Studies,Shandong University,Jinan,250100,China)

机构地区：[1]山东财经大学统计学院,济南250014 [2]山东大学金融研究院,济南250100

出　　处：《应用概率统计》2020年第5期467-482,共16页Chinese Journal of Applied Probability and Statistics

基　　金：国家自然科学基金项目(批准号:11871309、11371226);国家重点研发计划项目(批准号:2018YFA0703900);山东省自然科学基金项目(批准号:ZR2019MA035)资助。

摘　　要：资产价格跳跃作为波动估计和预测的一大影响因素,得到了广泛关注.Andersen等将跳跃引入到HAR波动预测模型中,构建了HAR-CJ模型.此后,大量文献对跳跃进行了研究,但尚未研究真伪跳跃对波动预测的影响.本文利用阈值技术,对真伪跳跃进行区分,并将其引入到HAR波动建模框架中,建立了HAR-CTFJ类模型及LHAR-CTFJ类模型,进一步研究了真伪跳跃对波动预测的影响.结果表明:真实跳跃对波动预测具有显著影响,而伪跳跃的影响并不显著.并且SPA检验结果表明,与HAR-CJ模型相比,HAR-CTJ、LHAR-CTJ模型具有更好的波动预测能力.Since the jump of an asset price has a strong effect on the estimate and forecast volatility,it has received widespread attention.Following HAR-CJ model introduced by Andersen et al,lots of works focus on this problem.In this paper,through a threshold technique,we distinguish the true and false jumps.Then we introduce two models,HAR-CTFJ model and LHAR-CTFJ model.Our result shows that the effect from the true jumps is significant while that from the false jumps is not.Moreover,the SPA test shows that our models(i.e.HAR-CTJ and LHAR-CTJ)are better than the classical HAR-CJ model in the prediction of volatility.

关 键 词：真伪跳跃 HAR模型 HAR-CTFJ模型 LHAR-CTFJ模型 SPA检验 

分 类 号：F830.91[经济管理—金融学] O212.6[理学—概率论与数理统计]