多重分形视角下的中美股市风险测度研究  

Research on Risk Measurement of Chinese and American Stock Markets from the Perspective of Multifractals

作　　者：董寅霄 Yinxiao Dong(School of Management,University of Shanghai for Science and Technology,Shanghai,200093,China)

机构地区：[1]上海理工大学,上海200093

出　　处：《管理科学与研究（中英文版）》2023年第8期22-31,共10页Management Science and Research

摘　　要：本文采用MFDFA对中美两国股市的多重分形特征进行研究,并建立了MSM模型来测度中美股市的波动性。实证结果表明上证指数和标普500指数收益率都不服从标准正态分布,都具有明显的多重分形特征,而多重分形的主要来源为收益率尖峰厚尾的分布和波动的长记忆性。MSM模型综合考虑了股市存在的多分形特征,采取MSM模型对上证指数和标普500指数的收益率进行拟合,结果表明其风险预测水平总体优于GARCH和EGARCH模型。This paper uses MFDFA to study the multifractal characteristics of the stock markets of China and the United States,and establishes the MSM model to measure the volatility of both stock markets.The empirical result shows that the returns of the SSEC Index and the S&P 500 Index do not obey the standard normal distribution,and both have obvious multifractal characteristics.The MSM model comprehensively considers the multifractal characteristics of the stock market,and we use the MSM model to fit the returns of the SSEC Index and the S&P 500 Index.The result shows that its risk prediction level is generally better than the GARCH model and EGARCH model.

关 键 词：MFDFA MSM模型 VAR 风险度量 

分 类 号：F83[经济管理—金融学]