Bayesian Chain Ladder Models

Guangyuan Gao ()
Additional contact information
Guangyuan Gao: Renmin University of China, School of Statistics

Chapter Chapter 4 in Bayesian Claims Reserving Methods in Non-life Insurance with Stan, 2018, pp 73-115 from Springer

Abstract: Abstract We study the Bayesian chain ladder models and their extensions in this chapter. In Sect. 4.1, the non-life insurance claims reserving background is reviewed. There are two parts in this section. The first part reviews claims reserving terminology. The second part summarizes widely used traditional reserving methods, including the chain ladder (CL) method and the Bornhuetter-Ferguson (BF) method. Stochastic models are discussed in Sects. 4.2 and 4.3. We focus on a Bayesian over-dispersed Poisson (ODP) model with an exponential decay curve component (Verrall et al. 2012). Reversible jump MCMC is used to simulate a sample from this model. In Sect. 4.4, we propose a compound model based on the payments per claim incurred (PPCI) method. A fully Bayesian analysis blending with preliminary classical model checking is performed on the weekly benefit data set and the doctor benefit data set from WorkSafe Victoria, a workers compensation scheme in Victoria state of Australia. We compare our results with the PwC evaluation (Simpson and McCourt 2012) Chain ladder method .

Date: 2018
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-13-3609-6_4

Ordering information: This item can be ordered from
http://www.springer.com/9789811336096

DOI: 10.1007/978-981-13-3609-6_4

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().