用双广义线性模型预测非寿险未决赔款准备金  

To Predict Reserve for Outstanding Losses of Non-Life Insurance by Using Dual Generalized Liner Models

作　　者：毛泽春[1] 吕立新 

机构地区：[1]湖北大学商学院金融系 [2]北京证券有限责任公司

出　　处：《统计研究》2005年第8期52-55,共4页Statistical Research

基　　金：国家自然科学基金项目的资助(批号:10471076);山东省自然科学基金项目的资助(批号:Y2004A07);山东省社科规划研究项目(批号04BJJ31)

摘　　要：A model to predict Incurred But Not Neported Claims Reserving(IBNR)is studied in this paper.Double generalized linear models are applied to fit claims numbers data and average claims sizes data,respectively.The mean square error of prediction is shown also.The model generalize that of Tweedie’s compound Poisson.Moreover,an example on Swiss Motor Insurance data is exhibited,which is shown more efficient.A model to predict Incurred But Not Neported Claims Reserving （IBNR）is studied in this paper. Double generalized linear models are applied to fit claims numbers data and average claims sizes data, respectively. The mean square error of prediction is shown also. The model generalize that of Tweedie＇ s compound Poisson. Moreover, an example on Swiss Motor Insurance data is exhibited, which is shown more efficient.

关 键 词：双广义线性模型 未决赔款准备金 广义线性模型 Tweedie类复合Poisson模型 保险业 

分 类 号：F840[经济管理—保险]