Fitting standard claims by Generalized Linear Models

被引:0
作者
Gogola, Jan [1 ]
机构
[1] Univ Pardubice, Fak Ekon Spravni, Pardubice, Czech Republic
来源
MANAGING AND MODELLING OF FINANCIAL RISKS, 8TH INTERNATIONAL SCIENTIFIC CONFERENCE, PTS I & II | 2016年
关键词
Generalized linear models; Gamma distribution; R language; likelihood function; risk classification;
D O I
暂无
中图分类号
F8 [财政、金融];
学科分类号
0202 ;
摘要
This article deals with the issue of creating homogenous tariff classes of non-life insurance and modelling the cost of standard claims of each tariff class. We use a Generalized Linear Models (GLM) for the purpose of finding significant risk factors and also to determine the cost of standard claims of the individual tariff classes. The theoretical part will be completed by application on a typical heterogeneous portfolio of the Motor Third Party Liability (MTPL). All calculations were performed using the R software. The result of the GLM is a multiplicative model where the cost of standard claim of a particular tariff class is given as a product of the cost of standard claim of the reference class and the relativities of the tariff class.
引用
收藏
页码:227 / 234
页数:8
相关论文
共 9 条
[1]  
Chongsuvivatwong V., 2012, EPICALC EPIDEMIOLOGI
[2]  
COX DR, 1972, J R STAT SOC B, V34, P187
[3]  
Denuit M., 2005, MATH ASSURANCE NONVI, VII
[4]  
Fox J., 2018, An R Companion to Applied Regression
[6]  
Marechal, 2007, ACTUARIAL MODELING C
[7]  
Nelder J.A., 1989, GEN LINEAR MODELS 2
[8]  
Pournelle G. H., 1953, Journal of Mammalogy, V34, P133, DOI 10.1890/0012-9658(2002)083[1421:SDEOLC]2.0.CO
[9]  
2