索赔次数的贝叶斯预测与信度近似  

The Bayesian Prediction and Credibility Approximate of Claim Number

作　　者：章溢 周金亮 ZHANG Yi;ZHOU Jinliang(School of Finance,Jiangxi Normal University,Nanchang Jiangxi 330022,China;School of Mathematics and Statistics,Jiangxi Normal University,Nanchang Jiangxi 330022,China)

机构地区：[1]江西师范大学财政金融学院,江西南昌330022 [2]江西师范大学数学与统计学院,江西南昌330022

出　　处：《江西师范大学学报（自然科学版）》2021年第4期353-361,共9页Journal of Jiangxi Normal University(Natural Science Edition)

基　　金：国家自然科学基金(71761019);江西省自然科学基金(20202BABL201001);江西省教育厅科学技术研究重点课题(GJJ200304)资助项目。

摘　　要：该文先对保单的索赔次数建立了贝叶斯模型;然后,根据样本分布和先验分布已知或未知分3种情形讨论了索赔次数的贝叶斯预测及信度预测,并给出了结构参数的估计方法;最后,通过数值模拟的方法对3个预测的均方误差和收敛性进行了比较.The Bayesian model is established for the number of claims of the insurance policy.According to whether the sample distribution and the prior distribution are known,the Bayesian prediction and credibility approximate claim number are discussed in three kinds of situations,and the estimation method of structural parameters is given.Finally,the convergences and the mean square errors of the three predictions are compared by numerical simulation.

关 键 词：泊松分布 伽马分布 贝叶斯预测 信度近似 结构参数 

分 类 号：O212.9[理学—概率论与数理统计]