SolvencyⅡ框架下非寿险一年期准备金风险的度量  

Research on the Measure of Non-life One-year Reserving Risk in Solvency Ⅱ

作　　者：刘乐平[1] 高磊[1] 王洋[1] 

机构地区：[1]天津财经大学统计学系,天津300222

出　　处：《数理统计与管理》2017年第1期126-138,共13页Journal of Applied Statistics and Management

基　　金：国家自然科学基金(71171139;71371138;71401069);天津财经大学研究生科研资助计划(2014TCB03)的资助

摘　　要：在欧盟以风险为核心的Solvency II监管框架下,非寿险准备金传统评估问题正向准备金风险管理新问题转化,准备金风险的识别、度量与控制已成为非寿险精算理论和实务重点关注的前沿问题。本文系统讨论非寿险一年期准备金风险的概念及其度量模型与方法。首先,通过实例直观阐述一年期准备金风险与索赔进展结果(CDR)的内涵;其次,基于贝叶斯对数正态模型,利用MCMC方法和R软件,随机模拟CDR的预测分布,并用CDR预测分布的统计特征来度量非寿险一年期准备金风险;最后,将欧洲保险公司实际索赔数据代入以上模型和步骤进行实证分析。研究表明,基于MCMC随机模拟方法获得的CDR预测分布,能够更加稳健和有效地度量非寿险一年期准备金风险。In this paper, we first clarify the meaning of one-year reserving risk and introduce some relevant measuring methods under Solvency Ⅱ regulations. And then based on the Bayesian Log-Normal model, we use simulation method to obtain the predictive distribution of CDR, from which we can get some measures of reserving risk. An empirical example using real business data shows that the predictive distribution of the CDR contains more information than the MSEP of CDR, so the measure of one-year reserving risk based on predictive distribution is more effective and accurate. Our study has not only enriched the methodology of one-year reserving risk, but also provided a reference for the 2nd generation solvency regulatory and supervisory system of China.

关 键 词：CDR预测分布 一年期准备金风险 MCMC 

分 类 号：F222.3[经济管理—国民经济] O212[理学—概率论与数理统计]