基于RT-GAS Copula模型的经济金融行业非对称相依性及风险溢出研究  

Research on the Asymmetric Interdependence and Risk Spillover of Economic and Financial Industries Based on RT-GAS Copula Model

作　　者：徐君 郭宝才[2] Xu Jun;Guo Baocai

机构地区：[1]杭州电子科技大学经济学院 [2]浙江工商大学统计与数学学院

出　　处：《统计研究》2023年第5期64-77,共14页Statistical Research

基　　金：国家社会科学基金一般项目“条件视角下参数估计对统计质量控制图的影响与修正改进研究”(18BTJ037);全国统计科学研究重点项目“过程参数未知下的在线监控问题研究”(2019LZ34);浙江省属高校基本科研业务费——青年教师科研创新专项一般项目“基于高频数据的动态Copula模型及其在市场相依性研究中的应用”(GK229909299001-227)。

摘　　要：考虑到实体经济行业与金融行业间的相依关系存在杠杆效应,本文采用GJR门限结构将杠杆效应纳入包含高频信息的广义已实现自回归得分Copula(GRAS Copula)模型中,构建广义已实现门限自回归得分Copula(RT-GAS Copula)模型。利用RT-GAS Copula模型揭示实体经济行业与金融行业间时变相依关系对行业收益的非对称响应,并进一步分析经济金融行业间风险溢出的非对称性和时变特征。研究发现:各行业间的相依关系存在显著的杠杆效应,某一行业收益的上涨和下跌对该行业与其他行业间时变相依关系的影响是非对称的;行业间的相依关系会受到国家调控政策和各类市场风险事件的影响;行业间的系统性风险溢出存在非对称性,且会受到严重风险事件的影响。此外,有效性检验结果表明,当行业间相依关系存在显著杠杆效应时,RT-GAS Copula模型的拟合和预测能力优于现有时变Copula模型。Considering that there is a leverage effect in the interdependence between the real economy and financial industries,the GJR threshold structure is used to incorporate the leverage effect into the Generalized Realized Autoregressive Score Copula(GRAS Copula)model containing high-frequency information to construct the Realized Threshold GAS Copula(RT-GAS Copula)model.Based on this,we use the RT-GAS Copula model to reveal the asymmetric response of the time-varying interdependence between the real economy and the financial industries on industry returns,and further analyze the asymmetric and time-varying characteristics of risk spillovers between the real economy and financial industries.The results show that:first,the interdependencies between various industries have a significant leverage effect,and the rise and fall of one industry’s return have asymmetric effect on the time-varying interdependencies between that industry and other industries;second,the inter-industry interdependencies are affected by national regulatory policies and various market risk events;third,the systematic risk spillovers between industries are asymmetric and affected by severe risk events.In addition,the validity test results show that the in-sample fitting and out-of-sample prediction capabilities of the RT-GAS Copula model are better than the existing time-varying Copula models when there is a significant leverage effect of inter-industry interdependence.

关 键 词：相依关系 杠杆效应 GJR门限结构 RT-GAS Copula模型 风险溢出 

分 类 号：F830[经济管理—金融学]