基于商业银行内部数据的KMV模型实证研究  

Research of KMV Model Based On Interior Data of Commercial Banks

作　　者：顾乾屏[1] 唐宁 王涛[3] 刘明 

机构地区：[1]中国工商银行总行,北京100140 [2]中国工商银行浙江分行,浙江杭州310009 [3]中国工商银行遵义分行,贵州遵义563000 [4]中国工商银行湖南分行,湖南长沙410005

出　　处：《金融理论与实践》2010年第1期60-63,共4页Financial Theory and Practice

摘　　要：本文借助KMV模型框架,对商业银行拥有的大量公司财务报表数据运用统计方法进行模型参数估计,计算得到了非上市公司的违约距离和经验函数,实现了违约概率的模型估计。实证表明,我国公司在违约距离或违约数量上的真实概率分布均呈现显著的T分布和肥尾特性;违约距离具有较高的风险区分能力;由会计信息进行参数估计的模型导出的具有较高的风险标志精度;进而表明基于会计报表数据的违约风险模型和基于资本市场数据的模型在实证上的有效性非常近似。Based on the principle of KMV model and statistical method and using internal financial data of commercial banks to estimate the parameters of KMV model, this paper simulates the distance to default and the EDF for non-listed companies and calculates the probability of default. The research demonstrates that the distribution of samples has the characteristic of T distribution and ＂fat tail＂, the distance to default has a more precise ability to distinguish the credit risk, the EDF which based on financial data can reveals the degree of credit risk exactly, the model based on bond market data and financial data have the same efficiency for the default risk estimation.

关 键 词：信用风险 KMV模型 违约距离 违约概率 EDF 

分 类 号：F830[经济管理—金融学]