Template-type: ReDIF-Paper 1.0
Author-Name: D. Kuang
Author-Email: di.kuang@aonbenfield.com
Author-Workplace-Name: Aon, 8 Devonshire Square, London
Author-Name: B. Nielsen
Author-Email: bent.nielsen@nuffield.ox.ac.uk
Author-Workplace-Name: Nuffield College, Oxford.
Author-Name: J. P. Nielsen
Author-Email: Jens.Nielsen.1@city.ac.uk
Author-Workplace-Name: Cass Business School, City University London.
Title: Chain-Ladder as Maximum Likelihood Revisited
Abstract: It has long been known that maximum likelihood estimation
in a Poisson model reproduces the chain-ladder technique. We revisit this
model. A new canonical parametrisation is proposed to circumvent the inherent
identification problem in the parametrisation. The maximum likelihood
estimators for the canonical parameter are simple, interpretable and easy
to derive. The boundary problem where all observations in one particular
development year or on particular underwriting year is zero is also analysed.
Keywords: Boundary problem, canonical parameter, chain-ladder, identification problem, 
maximum likelihood, Poisson model
X-Classification-JEL:
Length: 18 pages
Creation-Date: 2009-08-21
Number: 2009-W08
File-URL: 
File-Format: application/pdf
Handle: RePEc:nuf:econwp:0908