基于整体经验模态分解的金融高频数据波动率估计研究  

Volatility estimation of financial high frequency data based on ensemble empirical modal decomposition method

作　　者：秦喜文 周红梅 董小刚 郭佳静 冯阳洋 QIN Xi-wen;ZHOU Hong-mei;DONG Xiao-gang;GUO Jia-jing;FENG Yang-yang(School of Mathematics and Statistics,Changchun University of Technology,Changchun 130012,China)

机构地区：[1]长春工业大学数学与统计学院,吉林长春130012

出　　处：《东北师大学报（自然科学版）》2020年第3期89-95,共7页Journal of Northeast Normal University(Natural Science Edition)

基　　金：国家自然科学基金资助项目(11301036,11226335);吉林省教育厅科研项目(JJKH20170540KJ).

摘　　要：针对金融高频数据波动率的估计问题,借鉴小波变换思想,首次利用整体经验模态分解方法实现了高频数据波动率估计.首先,通过模拟数据验证了方法的可行性和有效性;其次,以日内高频数据为研究对象,并将分别利用经验模态分解和整体经验模态分解方法计算所得的波动率与已实现波动率进行了对比.结果表明,自适应分解方法可有效实现高频数据波动率估计,但整体经验模态分解要优于经验模态分解方法.该方法为高频数据波动率的非参数估计提供了新的解决途径,具有重要的推广与应用价值.To solve the problem of volatility estimation of high-frequency financial data,this paper proposes an ensemble empirical mode decomposition method based on the idea of wavelet transform to estimate the volatility of high-frequency financial data.Firstly,the feasibility and validity of the method are validated by simulation data.Secondly,the intra-day high frequency data is taken as the research object,and the calculated volatility using empirical mode decomposition and ensemble empirical mode decomposition are compared with the realized volatility.The results show that the adaptive decomposition method can effectively estimate the volatility of high-frequency data,but the ensemble empirical mode decomposition method is better than the empirical mode decomposition method.This method provides a new solution for the non-parametric estimation of high-frequency data volatility,and has important theoretical and application value.

关 键 词：高频数据 对数收益率 整体经验模态分解方法 波动率估计 

分 类 号：O29[理学—应用数学]