中国股市跨行业系统性风险空间溢出关联及风险预测分析——基于尾部风险网络模型

doi:10.16381/j.cnki.issn1003-207x.2019.1649

摘要/Abstract

摘要： 基于条件风险价值CoVaR和SIM单指数分位数回归技术，选取2012-2018年我国股市24行业指数周频数据，构建时变的跨行业尾部风险网络，通过网络拓扑结构反映系统性风险的空间关联及潜在变化趋势。此外，引入ARDL模型探究网络结构和宏观经济变量对股市系统性风险的长短期效应，最后对系统性风险进行预测。结果表明：(1)我国股市行业板块间存在明显的系统性风险空间关联和传染效应，风险溢出网络具有“小世界”特征；(2)网络连边集中度HHI呈明显的周期性变化。在尾部事件期间，HHI指标显著增加，风险网络呈较单一的中心节点结构，网络稳定性差；(3)通过节点风险传播强度和中心化程度发现，仅通过节点内部属性判断节点的系统重要性已不够全面和准确，应结合节点在网络中的位置和关联关系来判断；信息技术、医疗保健、商业和专业服务行业是风险网络中最有影响力的行业；(4)通过ARDL-ECM模型发现网络连边集中度是系统性风险的主要影响因素，并对股市系统性风险进行了高度准确的预测。本研究可为监管机构有效识别我国股市中有影响力的行业提供参考，依据关键行业的溢出关联制定针对性的风险防范措施，同时对风险溢出效应设立预警机制。

关键词: 系统性风险, 溢出关联, 尾部风险网络, 连边集中度, ARDL模型

Abstract: Financial markets have become remarkably volatile since 2008 global financial crisis. Systemic risk in the financial sector triggered by tail events can spread quickly across markets and even between countries. In the recent years, high volatility in stock prices and market crashes (i.e., the “money shortage” in 2013, the “stock disaster” in 2015 and the “COVID-19” in 2020) have been witnessed more frequent and severe. It is noted that financial systemic risks have a significant “generation-contagion-reinfection” mechanism. Although there is cross-institutional transmission, the problem of cross-market and cross-sector transmission have become increasingly prominent. Risk contributions vary across sectors and the risk contributions of individual institutions depend highly on their sect oral affiliations. Therefore, it is particularly important to analyze the systemic risk spatial spillover cross-industry in China’s stock market, identify the most influential industries, capture the source of risks and establish the systemic risk prediction model.

Key words: system risk, spillover correlation, tail risk network, edge concentration, ARDL model

中图分类号:

F832.5

张伟平, 庄新田, 王健. 中国股市跨行业系统性风险空间溢出关联及风险预测分析——基于尾部风险网络模型[J]. 中国管理科学, 2021, 29(12): 15-28.

ZHANG Wei-ping, ZHUANG Xin-tian, WANG Jian. Systematic Risk Spatial Spillover Correlation and Risk Prediction Analysis of Cross-industry in China’ Stock Market——Based on The Tail Risk Network Model[J]. Chinese Journal of Management Science, 2021, 29(12): 15-28.

参考文献

［1］沈丽,刘媛,李文君.中国地方金融风险空间关联网络及区域传染效应：2009-2016［J］.管理评论,2019, 8(31): 35-48.Shen Li, Liu Yuan, Li Wenjun.China’s regional financial risk spatial correlation network and regional contagion effect: 2009-2016［J］. Management Review, 2019, 8(31): 35-48.
［2］邓超, 陈学军. 基于多主体建模分析的银行间网络系统性风险研究［J］. 中国管理科学, 2016, 24(1): 67-75.Deng Chao, Chen Xuejun. Studyon multi-agent models analyses for systemic risk from the interbank network［J］. Chinese Journal of Management Science, 2016, 24(1): 67-75.
［3］ Acemoglu D, Ozdaglar A, Tahbaz-Salehi A.Systemic risk and stability in financial networks［J］. American Economic Review, 2015, 105(2): 564-608.
［4］ Anand K, Craig B, Peter G V. Filling in the blanks: network structure and interbank contagion［J］. Quantitative Finance, 2015, 15(4): 1-12.
［5］欧阳红兵, 刘晓东. 中国金融机构的系统重要性及系统性风险传染机制分析——基于复杂网络视角［J］. 中国管理科学, 2015, 23(10): 30-37.Ouyang Hongbing, Liu Xiaodong. An analysis of the systemic importance and systemic risk contagion mechanism of China’s financial institutions based on network analysis［J］.Chinese Journal of Management Science,2015, 23(10): 30-37.
［6］隋聪, 谭照林, 王宗尧. 基于网络视角的银行业系统性风险度量方法［J］. 中国管理科学, 2016, 24(5)：54-64.Sui Cong, Tan Zhaolin, Wang Zongyao. A network perspective measurement method for banking systemic risk［J］. Chinese Journal of Management Science,2016, 24(5)：54-64.
［7］ Adrian T, Brunnermeier M K. CoVaR［R］. National Bureau of Economic Research, 2011.
［8］ Jobst A. Operational Risk: The sting is still in the tail but the poison dependson the dose［M］. International Monetary Fund, 2007.
［9］ Acharya V V, Pedersen L H, Philippon T, et al. Measuring systemic risk［J］. The Review of Financial Studies, 2017, 30(1): 2-47.
［10］ Acharya V V, Richardson M. Is the insurance industry systemically risky［T］. Modernizing Insurance Regulation, 2014: 151-179.
［11］李守伟, 何建敏, 庄亚明等. 银行同业拆借市场的网络模型构建及稳定性［J］. 系统工程, 2010, 28(5): 20-24.Li Shouwei, He Jianmin, Zhuang Yaming, et al. The construction of network model of interbank markets and its stability［J］. Systems Engineering, 2010, 28(5): 20-24.
［12］杨子晖, 陈雨恬, 谢锐楷. 我国金融机构系统性金融风险度量与跨部门风险溢出效应研究［J］. 金融研究, 2018, 10: 19-37.Yang Zihui Chen Yutian, Xie Ruikai. Research on systemic risk measure and cross-sector risk spillover effect of financial institutions in China［J］. Journal of Financial Research, 2018, 10: 19-37.
［13］李政, 涂晓枫, 卜林. 金融机构系统性风险: 重要性与脆弱性［J］. 财经研究, 2019, 2: 100-113.Li Zheng, Tu Xiaofeng, Bu Lin. Systemic risks of financial institutions: important and vulnerability［J］. Journal of Finance and Economics, 2019, 2: 100-113.
［14］朱衡, 卓志. 保险公司系统重要性识别及其影响因素研究—基于系统性风险敞口与贡献的视角［J］. 保险研究, 2019, 3: 3-16.Zhu Heng, Zhuo Zhi. Systemic important of insurers and its influencing factors—Based on the exposure and contribution to systemic risk［J］. Insurance Studies, 2019, 3: 3-16.
［15］ Onnela J P, Chakraborti A, Kaski K, et al. Dynamics of market correlations: Taxonomy and portfolio analysis［J］. Physical Review E, 2003, 68(5): 056110.
［16］ Boginski V, Butenko S, Pardalos P M. Statistical analysis of financial networks［J］. Computational Statistics & Data Analysis, 2005, 48(2): 431-443.
［17］ Billio M, Getmansky M W. Lo A, et al. Econometric measures of connectedness and systemic risk in the finance and insurance sectors［J］. Journal of Financial Economics, 2012, 104: 535-559.
［18］ Diebold F X, Yilmaz K. On the network topology of variance decompositions: Measuring the connectedness of financial firms［J］. Journal of Econometrics, 2014, 182(1): 119-134.
［19］ Hrdle W K, Wang Weining, Yu Lining. TENET: Tail-event driven NETwork risk［J］. Journal of Econometrics, 2016, 192(2): 499-513.
［20］ Hautsch N, Schaumburg J, Schienle M. Financial network systemic risk contributions［J］. Review of Finance, 2015, 19(2): 685-738.
［21］李政，梁琪，涂晓枫. 我国上市金融机构关联性研究——基于网络分析法［J］. 金融研究,2016,8:95-110.Li Zheng, Liang Qi, Tu Xiaofeng. The connectedness of Chinese listed financial institutions: a study based on network analysis［J］. Journal of Financial Research,2016, 8: 95-110.
［22］胡利琴, 胡蝶, 彭红枫. 机构关联、网络结构与银行业系统性风险传染——基于VAR-NETWORK模型的实证分析［J］. 国际金融研究, 2018, 6: 53-64.Hu Liqin, Hu Die, Peng Hongfeng. Institutional association, network structure and banking systemic risk contagion—an empirical analysis based on VAR-NETWORK model［J］. Studies of International Finance, 2018, 6: 53-64.
［23］李邵芳, 刘晓星. 中国金融机构关联网络与系统性风险［J］. 金融经济学研究, 2018, 33(5): 34-48.Li Shaofang, Liu Xiaoxing. The interconnected network and systemic risk of China’s financial institutions［J］. Financial Economics Research, 2018, 33(5): 34-48.
［24］黄玮强, 郭慧敏, 姚爽. 尾部风险网络视角下的金融机构系统性风险贡献研究［J］. 运筹与管理, 2019, 28(3): 118-126.Huang Weiqiang, Guo Huimin, Yao Shuang. Study on financial institution’s systemic risk contribution from the perspective of tail risk networks［J］. Operations Research and Management Science, 2019, 28(3): 118-126.
［25］李立, 田益祥, 张弘磊. 考虑广义多维空间效应的S-VaR测算［J］. 系统工程理论与实践, 2015, 35(12): 3008-3016.Li Li, Tian Yixiang, Zhang Honglei.S-VaR calculation considering generalized multidimensional space effect［J］. Systems Engineering-Theory & Practice, 2015, 35(12): 3008-3016.
［26］高雄飞. 基于混沌最小二乘支持向量机的时间序列预测研究［J］. 数学的实践与认识, 2018, 48(8): 239-244.Gao Xiongfei. Time series prediction based on chaotixx least squares support vector machines［J］. Mathematics in Practice and Theory, 2018, 48(8): 239-244.
［27］ Chong E, Han C, Park F C. Deep learning networks for stock market analysis and prediction: methodology, data representations, and case studies［J］. Expert Systems with Applications, 2017, 83: 187-205.
［28］刘园, 韩斌. 我国银行信贷与房地产价格关系的实证研究［J］. 统计与决策, 2012, 17: 154-157.Liu Yuan, Han Bin. An empirical study on the relationship between bank rredit and real estate prices in my country［J］. Statistics & Decision, 2012, 17: 154-157.
［29］张云, 李秀珍, 唐海燕. 人民币贬值和升值的贸易效应一致吗？：基于ARDL误差校正方法的检验与比较［J］. 世界经济研究, 2017, 11: 52-64+136.Zhang Yun, Li Xiuzhen, Tang Haiyan. Does the devaluation and appreciation of RMB have the same trade effect? Test and comparison based on ARDL error-correction Methodology［J］. World Economy Studies, 2017, 11: 52-64+136.
［30］ Hrdle W K, Wang Weining, Yu Lining. TENET: Tail-event driven NETwork risk［J］. Journal of Econometrics, 2016, 192(2): 499-513.
［31］ Adrian T, Brunnermeier M K. CoVaR［J］. American Economic Review, 2016, 106: 1705-1741.
［32］ Chao S K, Hrdle W K, Wang W. Quantile regression in risk calibration［J］. SFB 649 Economic Risk Burlin Discussion Paper, 2012, 6.
［33］ Fan Jianqing, Li Runze. Variable selection via nonconcave penalized likelihood and its oracle properties［J］. Journal of the American Statistical Association, 2001, 96 (456): 1348-1360.
［34］ Fang Lei, Cheng Jiang, Su Fang. Interconnectedness and systemic risk: a comparative study based on systemically important ［J］. Pacific-Basin Finance Journal, 2019, 54: 147-158.
［35］ Pesaran M H, Shin Y, Smith R J. Bounds testing approaches to the analysis of level relationships［J］. Journal of Applied Econometrics, 2001, 16(3): 289-326.
［36］ Wang Gangjin, Jiang Zhiqiang, Lin Min, et al. Interconnectedness and systemic risk of China’s financial Institutions［J］. Emerging Markets Review, 2018, 35(6): 1-18.
［37］ Lewis C D.Industrial and business forecasting method: A practical guide to exponential smoothing and curve fitting［M］. Butterworth-Heinemann, London, 1982.

[1]	高倩倩, 范宏. 基于银行-资产双边网络模型的系统性风险及投资策略研究[J]. 中国管理科学, 2021, 29(7): 1-12.
[2]	赵林海, 陈名智. 金融机构系统性风险溢出和系统性风险贡献——基于滚动窗口动态Copula模型双时变相依视角[J]. 中国管理科学, 2021, 29(7): 71-83.
[3]	王耀东, 冯燕, 周桦. 保险业在金融系统性风险传染路径中起到“媒介”作用吗？——基于金融市场尾部风险传染路径的实证分析[J]. 中国管理科学, 2021, 29(5): 14-24.
[4]	马钱挺, 杨文珂, 何建敏. 基于多层网络的银企系统性风险研究[J]. 中国管理科学, 2021, 29(12): 1-14.
[5]	李红权, 何敏园, 黄莹莹. 我国金融机构的系统重要性评估:基于多元极值理论[J]. 中国管理科学, 2020, 28(5): 14-24.
[6]	姜闪闪, 范宏. 双渠道风险传染下银行系统稳定性分析[J]. 中国管理科学, 2020, 28(11): 51-60.
[7]	刘超, 李元睿, 姜超, 马玉洁, 刘宸琦, 谢启伟. 中国证券公司系统性风险测度及演化特征研究——来自20家上市证券公司的数据[J]. 中国管理科学, 2019, 27(5): 11-22.
[8]	姚鸿, 王超, 何建敏, 李亮. 银行投资组合多元化与系统性风险的关系研究[J]. 中国管理科学, 2019, 27(2): 9-18.
[9]	朱晓谦, 李靖宇, 李建平, 陈懿冰, 魏璐. 基于危机条件概率的系统性风险度量研究[J]. 中国管理科学, 2018, 26(6): 1-7.
[10]	叶五一, 谭轲祺, 缪柏其. 基于动态因子Copula模型的行业间系统性风险分析[J]. 中国管理科学, 2018, 26(3): 1-12.
[11]	曾裕峰, 简志宏, 彭伟. 中国金融业不同板块间风险传导的非对称性研究——基于非对称MVMQ-CAViaR模型的实证分析[J]. 中国管理科学, 2017, 25(8): 58-67.
[12]	隋聪, 谭照林, 王宗尧. 基于网络视角的银行业系统性风险度量方法[J]. 中国管理科学, 2016, 24(5): 54-64.
[13]	邓超, 陈学军. 基于多主体建模分析的银行间网络系统性风险研究[J]. 中国管理科学, 2016, 24(1): 67-75.
[14]	彭建刚, 易昊, 潘凌遥. 基于行业相关性的银行业信用风险宏观压力测试研究[J]. 中国管理科学, 2015, 23(4): 11-19.
[15]	刘孟飞, 王军. 系统性风险约束下的商业银行成本、利润效率比较研究[J]. 中国管理科学, 2015, 23(12): 27-34.