沪深300行业的相依结构突变性分析——基于动态R-Vine Copula
Analysis on the Sudden Change of Dependency Structure of CSI 300 Industries—Based on Dynamic R-Vine Copula
摘要: 本文结合滚动窗口技术构建高维动态R-Vine Copula模型,通过识别动态R-Vine Copula模型的结构突变点来判断高维变量间相依结构的动态变化,以此研究沪深300的10个一级行业在2015年至2022年的相依结构突变性。实证结果表明:2015年至2022年行业间的相依结构在2018年1月与2019年12月发生结构突变,将整体划分为3个突变区间,两次突变发生的原因受中美贸易战与新冠疫情影响的可能较大;三个突变区间内,沪深300行业间相依结构有较大变化,行业中心点由工业与可选消费转移至工业,再转移至可选消费;突变区间1内行业间多呈上下尾不对称的相依结构,而突变区间2内行业间大多表现出上下尾对称的相依结构,同时相依性有所增大,突变区间3内行业间多呈上下尾不对称的相依结构,且相依性有所降低。此外,新冠疫情期间沪深300行业投资组合的风险价值(VaR)与期望损失(ES)的绝对值相较于疫情前有所增大,但随着疫情影响的减弱,行业投资组合VaR与ES的值在2021年6月逐渐趋于与突变点前一致。
Abstract:
This paper uses the rolling window technology to build a high-dimensional dynamic R-Vine Copula model. By identifying the structural mutation points of the dynamic R-Vine Copula model, we can judge the dynamic changes of the dependence structure among high-dimensional variables, so as to study the dependent structure mutation of ten primary industries of CSI 300 from 2015 to 2022. The empirical results are obtained as follows: 1) from 2015 to 2022, the inter-industry dependence structure undergoes structural mutation in January 2018 and December 2019.The whole is divided into three mutation intervals ,and the reason for this mutation is likely to be affected by Sino US trade war and COVID-19; 2) within the three sudden change intervals, the dependency structure of CSI 300 industries has changed significantly, the industry center has shifted from industry and op-tional consumption to industry and then to optional consumption; 3) most of the industries in mu-tation interval 1 have an asymmetric dependency structure with upper and lower tails, while most of the industries in mutation interval 2 have an asymmetric dependency structure with upper and lower tails, and the dependency has increased. Most of the industries in mutation interval 3 have an asymmetric dependency structure with upper and lower tails, and the dependency has decreased. In addition, the absolute value of the value at risk (VaR) and the expected loss (ES) of CSI 300 sector portfolios during the COVID-19 are increasing compared with that before the mutation point. How-ever, with the weakening of the impact of the epidemic, the values of VaR and ES have gradually become consistent with that before the mutation point in June 2021.
参考文献
|
[1]
|
宁建楠, 易文德. 金融危机对中国股市各行业板块间相依结构的影响[J]. 系统工程, 2015, 33(11): 10-17.
|
|
[2]
|
李延双, 庄新田, 王健, 宫晓莉. 中美贸易摩擦对中国沪深股市行业板块的影响[J]. 管理科学学报, 2021, 24(10): 34-57.
|
|
[3]
|
崔金鑫, 邹辉文. 中国股市行业间高阶矩风险溢出效应研究[J]. 系统科学与数学, 2020, 40(7): 1178-1204.
|
|
[4]
|
Bedford, T. and Cooke, R.M. (2002) Vines: A New Graphical Model for Dependent Random Varia-bles. Annals of Statistics, 30, 1031-1068. [Google Scholar] [CrossRef]
|
|
[5]
|
DißMann, J., Brechmann, E.C., et al. (2013) Selecting and Estimating Regular Vine Copula and Application to Financial Returns. Computational Statistics & Data Analysis, 59, 52-69. [Google Scholar] [CrossRef]
|
|
[6]
|
Brechmann, E.C. and Czado, C. (2013) Risk Management with High-Dimensional Vine Copulas: An Analysis of the Euro Stoxx 50. Statistics & Risk Modeling, 30, 307-342. [Google Scholar] [CrossRef]
|
|
[7]
|
朱鹏飞, 唐勇, 张仁坤. 国际主要股票市场联动性——基于藤Copula-HAR-RV模型[J]. 系统工程, 2018, 36(9): 16-29.
|
|
[8]
|
唐勇, 戴艺敏, 朱鹏飞. 基于GARCH-Vine-Copula模型的P2P网贷市场区域利率相依性研究[J]. 浙江金融, 2019(3): 20-28.
|
|
[9]
|
张卓群, 张涛. 中国城市房地产价格关联与风险传染防范研究——基于ARIMA-R-Vine Copula模型的分析[J]. 价格理论与实践, 2021(7): 49-53+164
|
|
[10]
|
邹辉文, 朱丽娟. 基于R-Vine Copula模型的国际原油与国际股市间的风险传染效应研究[J]. 电子科技大学学报(社科版), 2021, 23(4): 106-112.
|
|
[11]
|
侯仲凯, 何卓静, 周利国. 行业间市场风险相依结构及其危机传染效应[J]. 金融经济学研究, 2018, 33(2): 71-83.
|
|
[12]
|
郭文伟. 国内外股市相依结构演化及其危机传染效应研究[J]. 国际金融研究, 2016(10): 63-73.
|