我国金融机构的系统性金融风险评估——基于极端分位数回归技术的风险度量  

Measuring Systemic Financial Risk of China's Financial Institution——Applying Extremal Quantile Regression Technology and CoVaR Model

作　　者：陈守东[1,2] 王妍[2] 

机构地区：[1]吉林大学数量经济研究中心,吉林长春130012 [2]吉林大学商学院,吉林长春130012

出　　处：《中国管理科学》2014年第7期10-17,共8页Chinese Journal of Management Science

基　　金：教育部人文社科重点研究基地重大项目(2009JJD790015);国家社科基金项目(12BJY158)

摘　　要：本文将极值理论引入到系统性金融风险度量中,通过极端分位数回归技术估计我国33家上市金融机构对金融系统整体的风险贡献,并识别出我国系统重要性金融机构。研究结果表明,我国金融机构的市场价值总资产收益率呈现明显的非正态分布特征,使用极端分位数回归技术可以更准确的度量尾部的风险联动性;银行类金融机构的系统性风险贡献水平最高且波动变化最大,系统性风险贡献排名前十的金融机构基本为银行类机构;证券类、保险类、信托类金融机构的风险贡献水平相对较低;通过与其他研究的对比发现,考虑到极端情形下的尾部风险联动性时,股份制商业银行对金融系统的风险贡献上升。本文的研究为系统重要性金融机构的宏观审慎监管提供了实证依据。Based on the extreme theory, a new approach is presented for measuring systemic financial risk. Using extremal quantile regression, 33 listed financial institutions ~ contributions to the systemic risk of financial system are estimated and systemically important institutions in China＇s financial system are recag- njzed. It is found that, the distributions of the growth rate of market valued total assets and the co-movement of the tail risk can be accurately estimated using the extremal quantile regression. The level and vari- ance of the systemic risk contribution in bank sector are the highest. The top ten systemically important financial institutions are almost in bank sector. The levels of systemic contribution in security sector, insurance sector and trust sector are relatively low. Moreover, systemic contributions of joint-stock commercial banks are higher in our study. An empirical tool is provided in this paper for further macro-prudential regulation of systemically important institutions.

关 键 词：系统性金融风险 CoVaR 极端分位数回归 风险度量 

分 类 号：F830[经济管理—金融学]