基于分位数因子VAR模型的金融机构间特质风险关联研究

doi:10.12341/jssms22433

系统科学与数学 ›› 2023, Vol. 43 ›› Issue (2): 431-451.DOI: 10.12341/jssms22433

基于分位数因子VAR模型的金融机构间特质风险关联研究

杜焱¹, 欧阳资生², 周学伟²

1. 湖南工商大学财政金融学院, 长沙 410205;
2. 湖南师范大学商学院, 长沙 410081

收稿日期:2022-06-15 修回日期:2022-08-03 出版日期:2023-02-25 发布日期:2023-03-16
通讯作者: 周学伟,Email:xueweizhou@hunnu.edu.cn
基金资助:
国家社会科学基金重点项目(21ATJ009),湖南省教育厅重点科研项目(18A294)资助课题.

PDF ( 1 ) 引用

杜焱,欧阳资生,周学伟. 基于分位数因子VAR模型的金融机构间特质风险关联研究[J]. 系统科学与数学, 2023, 43(2): 431-451.

DU Yan, OUYANG Zisheng, ZHOU Xuewei. Idiosyncratic Risk Connectedness Among Financial Institutions: A Quantile Factor VAR Approach[J]. Journal of Systems Science and Mathematical Sciences, 2023, 43(2): 431-451.

Idiosyncratic Risk Connectedness Among Financial Institutions: A Quantile Factor VAR Approach

DU Yan¹, OUYANG Zisheng², ZHOU Xuewei²

1. School of Finance, Hunan University of Technology and Business, Changsha 410205;
2. School of Business, Hunan Normal University, Changsha 410081

Received:2022-06-15 Revised:2022-08-03 Online:2023-02-25 Published:2023-03-16

文章采用最新发展的QFVAR(Quantile Factor VAR)模型,借助市场因子消除误差项中的横截面相关性,从而研究中国36家上市金融机构间的特质风险关联,并通过分位数回归估计,考察了金融机构间的均值风险传染和尾部风险传染,最后从风险溢出和风险溢入角度,探讨了金融机构特质风险的主要来源.研究发现:1)金融机构特质风险关联会随着分位数发生显著变化,相较条件均值和条件中位数,特质风险在两侧尾部存在强烈的时变关联效应.2)特质风险的均值传染主要集中在部门内,而尾部传染则表现出明显的跨部门效应,其中右尾的风险传染强度更高.3)在金融市场平稳期,证券部门具有较高的特质风险溢出水平,而在金融市场危机期,银行部门具有较高的特质风险溢出水平.文章的研究结果对监管部门防范化解金融风险具有借鉴意义,有助于其从特质冲击角度,加深对金融风险传染机制的理解.

关键词： 特质风险, 金融机构, 尾部关联, 因子结构, 分位数回归

Under the background of uneven and unstable economic recovery, the key to preventing and defusing financial risk is to capture the characteristics of risk connectedness among financial institutions. Different from the existing risk connectedness literature, this paper uses the QFVAR model to study the idiosyncratic risk connectedness among 36 listed financial institutions in China. The main conclusions are as follows: First, compared with the conditional mean and the conditional median, the connectedness level of idiosyncratic risk in both tails is higher and has time-varying characteristics. These important features of idiosyncratic risk connectedness are obscured in models estimated using conventional conditional mean estimators. Second, the mean contagion is mainly concentrated within sectors, while the tail contagion has cross-sector effects. The cross-sector contagion of the right tail is more obvious, mainly concentrated in large state-owned banks. Finally, during the market stable period, the securities sector has a higher level of risk spillover, while during the market crisis period, the banking sector has a higher risk spillover level.

Key words: Idiosyncratic risk, financial institution, tail connectedness, factor structure, quantile regression

MR(2010)主题分类:

60E05
91B28

分享此文:

[1] Acemoglu D, Ozdaglar A, Tahbaz-Salehi A. Systemic risk and stability in financial networks. American Economic Review, 2015, 105(2):564-608.
[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. 中国管理科学, 2016, 24(1):65-75. (Deng C, Chen X J. Studyon multi-agent models analyses for systemic risk from the interbank network. Chinese Journal of Management Science, 2016, 24(1):65-75.)
[3] 黄金波, 李仲飞, 丁杰. 基于非参数核估计方法的均值-VaR模型. 中国管理科学, 2017, 25(5):1-10. (Huang J B, Li Z F, Ding J. A mean-VaR portfolio selection model based on nonparametric kernel estimation method. Chinese Journal of Management Science, 2017, 25(5):1-10.)
[4] 刘炳越, 姬强, 范英. 黄金是否为原油的"避险天堂"?——基于组合收益及其波动视角. 中国管理科学, 2018, 26(11):1-10. (Liu B Y, Ji Q, Fan Y. Is the gold safe haven of the oil? The portfolio return and volatility perspectives. Chinese Journal of Management Science, 2018, 26(11):1-10.)
[5] Patton A, Ziegel J F, Chen R. Dynamic semiparametric models for expected shortfall (and Value-at-Risk). Journal of Econometrics, 2019, 211(2):388-413.
[6] 李嘉弘, 李平. COVID-19疫情期间比特币与中国金融市场主要资产的关系研究. 管理评论, 2021, 33(11):286-297. (Li J H, Li P. The relationship between bitcoin and chinese financial markets during COVID-19. Management Review, 2021, 33(11):286-297.)
[7] Adrian T, Brunnermeier M K. CoVaR. American Economic Review, 2016, 106(7):1705-1741.
[8] Acharya V V, Pedersen L H, Philippon T, et al. Measuring systemic risk. Review of Financial Studies, 2017, 30(1):2-47.
[9] Banulescu G D, Dumitrescu E I. Which are the SIFIs? A component expected shortfall approach to systemic risk. Journal of Banking and Finance, 2015, 50]:575-588.
[10] Eckernkemper T. Modeling systemic risk:Time-varying tail dependence when forecasting marginal expected shortfall. Journal of Financial Econometrics, 2018, 16(1):63-117.
[11] 陈湘鹏, 周皓, 金涛, 等. 微观层面系统性金融风险指标的比较与适用性分析——基于中国金融系统的研究. 金融研究, 2019, (5):17-36. (Chen X P, Zhou H, Jin T, et al. Comparison and applicability analysis of micro-level systemic risk measures:A study based on China's financial system. Journal of Financial Research, 2019, (5):17-36.)
[12] 刘超, 刘彬彬. 金融机构尾部风险溢出效应——基于改进非对称CoVaR模型的研究. 统计研究, 2020, 37(12):58-74. (Liu C, Liu B B. Tail risk spillover of financial institutions——A study based on improved asymmetric CoVaR model. Statistical Research, 2020, 37(12):58-74.)
[13] 欧阳资生, 李虹宣, 杨希特. 网络舆情对中国上市金融机构系统性风险影响研究. 系统科学与数学, 2021, 41(5):1339-1354. (Ouyang Z S, Li H X, Yang X T. Research on the influence of network public opinion on the systemic risk of listed financial institutions in China. Journal of Systems Science and Mathematical Sciences, 2021, 41(5):1339-1354.)
[14] Brownlees C, Engle R F. SRISK:A conditional capital shortfall measure of systemic risk. The Review of Financial Studies, 2017, 30(1):48-79.
[15] Billio M, Getmansky M, Lo A W, et al. Econometric measures of connectedness and systemic risk in the finance and insurance sectors. Journal of Financial Economics, 2012, 104(3):535-559.
[16] Diebold F X, Yilmaz K. On the network topology of variance decompositions:Measuring the connectedness of financial firms. Journal of Econometrics, 2014, 182(1):119-134.
[17] Greenwood-Nimmo M, Nguyen V H, Rafferty B. Risk and return spillovers among the G10 currencies. Journal of Financial Markets, 2016, 31]:43-62.
[18] Demirer M, Diebold F X, Liu L, et al. Estimating global bank network connectedness. Journal of Applied Econometrics, 2018, 33(1):1-15.
[19] 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. 金融研究, 2018, (10):19-37. (Yang Z H, Chen Y T, Xie R K. Research on systemic risk measures and cross-sector risk spillover effect of financial institutions in China. Journal of Financial Research, 2018, (10):19-37.)
[20] 宫晓莉, 熊熊, 张维. 我国金融机构系统性风险度量与外溢效应研究. 管理世界, 2020, 36(8):65-82. (Gong X L, Xiong X, Zhang W. Research on systemic risk measurement and spillover effect of financial institutions in China. Management World, 2020, 36(8):65-82.)
[21] 刘程程, 苏治, 宋鹏. 全球股票市场间风险传染的测度、监管及预警. 金融研究, 2020, (11):94-112. (Liu C C, Su Z, Song P. Measurement, supervision and early warning of risk contagin among global stock markets. Journal of Financial Research, 2020, (11):94-112.)
[22] 崔金鑫, 邹辉文. 中国股市行业间高阶矩风险溢出效应研究. 系统科学与数学, 2020, 40(7):1178-1204. (Cui J X, Zhou H W. The higher moments risk spillover effects among stock market industries:Evidence from chinese stock market. Journal of Systems Science and Mathematical Sciences, 2020, 40(7):1178-1204.)
[23] Barigozzi M, Hallin M. Generalized dynamic factor models and volatilities:Recovering the market volatility shocks. The Econometrics Journal, 2016, 19(1):C33-C60.
[24] Barigozzi M, Hallin M, Soccorsi S. Identification of global and local shocks in international financial markets via general dynamic factor models. Journal of Financial Econometrics, 2019, 17(3):462-494.
[25] Ma Y R, Zhang D, Ji Q, et al. Spillovers between oil and stock returns in the US energy sector:Does idiosyncratic information matter? Energy Economics, 2019, 81]:536-544.
[26] 宫晓莉, 熊熊. 波动溢出网络视角的金融风险传染研究. 金融研究, 2020, (5):39-58. (Gong X L, Xiong X. A study of financial risk contagion from the volatility spillover network perspective. Journal of Financial Research, 2020, (5):39-58.)
[27] 欧阳资生, 周学伟, 谢楠. 中国金融机构时变关联性测度研究——来自频域视角的新证据. 系统工程理论与实践, 2022, 42(8):2087-2101. (Ouyang Z S, Zhou X W, Xie N. Time-varying connectedness measurement of Chinese financial institutions:New evidence from the frequency domain perspective. Systems Engineering——Theory & Practice, 2022, 42(8):2087-2101.)
[28] Caporin M, Pelizzon L, Ravazzolo F, et al. Measuring sovereign contagion in Europe. Journal of Financial Stability, 2018, 34]:150-181.
[29] Barigozzi M, Hallin M. A network analysis of the volatility of high dimensional financial series. Journal of the Royal Statistical Society:Series C (Applied Statistics), 2017, 66(3):581-605.
[30] Ando T, Greenwood-Nimmo M, Shin Y. Quantile connectedness:Modeling tail behavior in the topology of financial networks. Management Science, 2022, 68(4):2401-2431.
[31] Koenker R, Xiao Z. Quantile autoregression. Journal of the American Statistical Association, 2006, 101(475):980-990.
[32] 贾妍妍, 方意, 荆中博. 中国金融体系放大了实体经济风险吗. 财贸经济, 2020, (10):111-128. (Jia Y Y, Fang Y, Jing Z B. Does china's financial system amplify risks in the real economy? Finance and Trade Economics, 2022, (10):111-128.)
[33] Parkinson M. The extreme value method for estimating the variance of the rate of return. The Journal of Business, 1980, 53(1):61-65.
[34] 陈国进, 钟灵, 张宇. 我国银行体系的系统性关联度分析:基于不对称CoVaR. 系统工程理论与实践, 2017, 37(1):61-79. (Chen G J, Zhong L, Zhang Y. Systemic linkage in the chinese banking system:The asymmetric CoVaR approach. Systems Engineering——Theory & Practice, 2017, 37(1):61-79.)
[35] Huang Y, Luk P. Measuring economic policy uncertainty in China. China Economic Review, 2020, 59]:101367.
[36] Chatziantoniou I, Gabauer D, Stenfors A. Interest rate swaps and the transmission mechanism of monetary policy:A quantile connectedness approach. Economics Letters, 2021, 204]:109891.
[37] 梁琪, 李政, 郝项超. 中国股票市场国际化研究:基于信息溢出的视角. 经济研究, 2015, 50(4):150-164. (Liang Q, Li Z, Hao X C. The internationalization of Chinese stock market:Based on information spillover. Economic Research Journal, 2015, 50(4):150-164.)
[38] 方意, 荆中博, 吴姬, 等. 非核心负债、尾部依赖与中国银行业系统性风险. 世界经济, 2020, 43(4):123-144. (Fang Y, Jing Z B, Wu J, et al. Non-core Liabilities, tail dependence, and China's banking systemic risk. The Journal of World Economy, 2020, 43(4):123-144.)

[1]	蔡超, 黄聪聪, 董皓天. 分位数回归提升树模型及应用[J]. 系统科学与数学, 2022, 42(5): 1216-1233.
[2]	蔡超, 董皓天, 李丽. 分位数惩罚整合模型及其在商业银行系统性风险中的应用[J]. 系统科学与数学, 2022, 42(12): 3397-3411.
[3]	吕晓玲，王小宁，孙志猛. 删失分位数变系数回归模型的~FIC 模型平均估计[J]. 系统科学与数学, 2018, 38(7): 746-763.
[4]	王江峰，范国良，温利民. 删失指标随机缺失下回归函数的复合分位数回归估计[J]. 系统科学与数学, 2018, 38(11): 1347-1362.
[5]	余平，杜江，张忠占. 部分函数型线性可加分位数回归模型[J]. 系统科学与数学, 2017, 37(5): 1335-1350.
[6]	赵亮，杨战平. 一种针对实验数据的裕量和不确定性量化方法[J]. 系统科学与数学, 2016, 36(8): 1138-1149.

阅读次数

全文

摘要