An Application of Randomly Truncated Data Models in Reserving BNR Claims

Abstract
A compound Poisson model of IBNR claims is considered and methods of statistical inference under this model using the techniques well known from the analysis of survival time data are investigated. It is shown that the results on statistical analysis of non-parametric model for randomly truncated data can be used to obtain a simple estimate of IBNR claims which, among other things, allows for easy construction of confidence bounds.

Keywords: IBNR claims; Model of randomly truncated data

Volume
25:2
Page
123-131
Year
1999
Categories
Actuarial Applications and Methodologies
Reserving
Reserving Methods
Actuarial Applications and Methodologies
Reserving
Uncertainty and Ranges
Publications
Insurance: Mathematics & Economics