CREDIBILITY THEORY APPROACH TO THE CHAIN LADDER METHOD
The determination of the outstanding claims liability is one of the main tasks of an actuary. The claims data in a long-tail insurance business may be represented in the form of a runoff triangle. One method to predict the outstanding claims liability is the Chain Ladder Method (CLM). If the informa...
Saved in:
Main Author: | |
---|---|
Format: | Theses |
Language: | Indonesia |
Online Access: | https://digilib.itb.ac.id/gdl/view/19953 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Institut Teknologi Bandung |
Language: | Indonesia |
id |
id-itb.:19953 |
---|---|
spelling |
id-itb.:199532017-10-09T10:16:36ZCREDIBILITY THEORY APPROACH TO THE CHAIN LADDER METHOD YUNEIDI (NIM: 20813016); Pembimbing : Dumaria Rulina Tampubolon, Ph.D, BELINDA Indonesia Theses INSTITUT TEKNOLOGI BANDUNG https://digilib.itb.ac.id/gdl/view/19953 The determination of the outstanding claims liability is one of the main tasks of an actuary. The claims data in a long-tail insurance business may be represented in the form of a runoff triangle. One method to predict the outstanding claims liability is the Chain Ladder Method (CLM). If the information from past claims data is not enough, an actuary may use simultaneously the individual information (or the experience of the company itself) and the collective information (or the experience of the market). To utilize the information from both parties, a credibility approach to CLM is used and in this thesis the model applied is the non-parametric Buhlmann-Straub model. The CLM uses the information from one portfolio (runoff triangle) while the credibility model to the CLM also uses the information from several other portfolios (runoff triangles). The data analyzed in this thesis is taken from Winthertur Insurance Company (Gisler and Wutrich, 2008). It is obtained that for a particular runoff triangle, the prediction of the outstanding claims liability by the CLM maybe larger or smaller than that by the credibility model to CLM, depending on the historical claims data. However, for all the runoff triangles analyzed in this thesis, the mean square error (MSE) of the estimator of the outstanding claims liability by the CLM is greater that that by the credibility model to CLM. It is concluded that for the data used in this thesis, the prediction of the the outstanding claims liability obtained by the credibility model to the chain ladder method is better than that by the chain ladder method. text |
institution |
Institut Teknologi Bandung |
building |
Institut Teknologi Bandung Library |
continent |
Asia |
country |
Indonesia Indonesia |
content_provider |
Institut Teknologi Bandung |
collection |
Digital ITB |
language |
Indonesia |
description |
The determination of the outstanding claims liability is one of the main tasks of an actuary. The claims data in a long-tail insurance business may be represented in the form of a runoff triangle. One method to predict the outstanding claims liability is the Chain Ladder Method (CLM). If the information from past claims data is not enough, an actuary may use simultaneously the individual information (or the experience of the company itself) and the collective information (or the experience of the market). To utilize the information from both parties, a credibility approach to CLM is used and in this thesis the model applied is the non-parametric Buhlmann-Straub model. The CLM uses the information from one portfolio (runoff triangle) while the credibility model to the CLM also uses the information from several other portfolios (runoff triangles). The data analyzed in this thesis is taken from Winthertur Insurance Company (Gisler and Wutrich, 2008). It is obtained that for a particular runoff triangle, the prediction of the outstanding claims liability by the CLM maybe larger or smaller than that by the credibility model to CLM, depending on the historical claims data. However, for all the runoff triangles analyzed in this thesis, the mean square error (MSE) of the estimator of the outstanding claims liability by the CLM is greater that that by the credibility model to CLM. It is concluded that for the data used in this thesis, the prediction of the the outstanding claims liability obtained by the credibility model to the chain ladder method is better than that by the chain ladder method. |
format |
Theses |
author |
YUNEIDI (NIM: 20813016); Pembimbing : Dumaria Rulina Tampubolon, Ph.D, BELINDA |
spellingShingle |
YUNEIDI (NIM: 20813016); Pembimbing : Dumaria Rulina Tampubolon, Ph.D, BELINDA CREDIBILITY THEORY APPROACH TO THE CHAIN LADDER METHOD |
author_facet |
YUNEIDI (NIM: 20813016); Pembimbing : Dumaria Rulina Tampubolon, Ph.D, BELINDA |
author_sort |
YUNEIDI (NIM: 20813016); Pembimbing : Dumaria Rulina Tampubolon, Ph.D, BELINDA |
title |
CREDIBILITY THEORY APPROACH TO THE CHAIN LADDER METHOD |
title_short |
CREDIBILITY THEORY APPROACH TO THE CHAIN LADDER METHOD |
title_full |
CREDIBILITY THEORY APPROACH TO THE CHAIN LADDER METHOD |
title_fullStr |
CREDIBILITY THEORY APPROACH TO THE CHAIN LADDER METHOD |
title_full_unstemmed |
CREDIBILITY THEORY APPROACH TO THE CHAIN LADDER METHOD |
title_sort |
credibility theory approach to the chain ladder method |
url |
https://digilib.itb.ac.id/gdl/view/19953 |
_version_ |
1821119999746506752 |