Geodesic
Statistical Estimation Methods Benchmarking in R Using Insurance Claims Data
Mathematica Applicanda, Tome 51 (2023) no. 2, pp. 305-320.

Voir la notice de l'article provenant de la source Annales Societatis Mathematicae Polonae Series

The assessment of claim reserves is one of the components of risk management. This paper aims to analyze and to establish a realistic approach to claims reserving using generalized linear models for loss reserving. The chain ladder is formulated in a GLM context, and then after, the statistical distribution of the loss reserve is analyzed. Such structure is consequently used while testing the necessity for initiation from the chain ladder model and to formulate any required model extensions. The GLM allows the use of bootstrapping in estimating the prediction error. This is not the case with the standard chain ladder technique, which is a distribution-free method. The application of the generalized linear model cannot put back the actuarial judgment and business knowledge. Nevertheless, careful data analysis such as the generalized linear model substantially reorganizes any system and projection procedure. Based in one solid mathematical ground, it is more comfortable for the reserving actuary to explain his projections to the management board and underwriters. These models will be discussed using the claim data from the DMTPL (Domestic Motor Third Party Liability) portfolio of an Albanian insurance company.
DOI : 10.14708/ma.v51i2.7153
Classification : 62P05,62P05
Mots-clés : Generalized linear models, claims reserve, exponential dispersion family, chain ladder method 
@article{10_14708_ma_v51i2_7153,
     author = {Teuta Budlla and Kleida Haxhi and Etleva Llagami and Endri Raco and Oriana Zacaj},
     title = {Statistical {Estimation} {Methods} {Benchmarking} in {R} {Using} {Insurance} {Claims} {Data}},
     journal = {Mathematica Applicanda},
     pages = { 305--320},
     publisher = {mathdoc},
     volume = {51},
     number = {2},
     year = {2023},
     doi = {10.14708/ma.v51i2.7153},
     language = {pl},
     url = {http://geodesic.mathdoc.fr/articles/10.14708/ma.v51i2.7153/}
}
TY  - JOUR
AU  - Teuta Budlla
AU  - Kleida Haxhi
AU  - Etleva Llagami
AU  - Endri Raco
AU  - Oriana Zacaj
TI  - Statistical Estimation Methods Benchmarking in R Using Insurance Claims Data
JO  - Mathematica Applicanda
PY  - 2023
SP  -  305
EP  - 320
VL  - 51
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/articles/10.14708/ma.v51i2.7153/
DO  - 10.14708/ma.v51i2.7153
LA  - pl
ID  - 10_14708_ma_v51i2_7153
ER  - 
%0 Journal Article
%A Teuta Budlla
%A Kleida Haxhi
%A Etleva Llagami
%A Endri Raco
%A Oriana Zacaj
%T Statistical Estimation Methods Benchmarking in R Using Insurance Claims Data
%J Mathematica Applicanda
%D 2023
%P  305-320
%V 51
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/articles/10.14708/ma.v51i2.7153/
%R 10.14708/ma.v51i2.7153
%G pl
%F 10_14708_ma_v51i2_7153
Teuta Budlla; Kleida Haxhi; Etleva Llagami; Endri Raco; Oriana Zacaj. Statistical Estimation Methods Benchmarking in R Using Insurance Claims Data. Mathematica Applicanda, Tome 51 (2023) no. 2, pp.  305-320. doi : 10.14708/ma.v51i2.7153. http://geodesic.mathdoc.fr/articles/10.14708/ma.v51i2.7153/

Cité par Sources :