A Claims Persistence Process and Insurance

22 Pages Posted: 16 Jul 2009  

Charles S. Tapiero

NYU Polytechnic School of Engineering - Department of Finance and Risk Engineering

Pierre Vallois

affiliation not provided to SSRN

Date Written: September 27, 2008

Abstract

The purpose of this paper is to introduce and construct a state dependent counting and persistent random walk. Persistence is imbedded in a Markov chain for predicting insured claims based on their current and past period claim. We calculate for such a process, the probability generating function of the number of claims over time and as a result are able to calculate their moments. Further, given the claims severity probability distribution, we provide both the claims process generating function as well as the mean and the claim variance that an insurance firm confronts over a given period of time and in such circumstances. A number of results and applications are then outlined (such as a Compound Claim Persistence Process).

Keywords: Random walk, Persistence, Insurance claims, Value at risk

Suggested Citation

Tapiero, Charles S. and Vallois, Pierre, A Claims Persistence Process and Insurance (September 27, 2008). Insurance: Mathematics and Economics, Vol. 44, No. 3, 2009. Available at SSRN: https://ssrn.com/abstract=1433483

Charles S. Tapiero (Contact Author)

NYU Polytechnic School of Engineering - Department of Finance and Risk Engineering ( email )

Brooklyn, NY 11201
United States

Pierre Vallois

affiliation not provided to SSRN

Paper statistics

Downloads
97
Rank
227,506
Abstract Views
774