Colloque / Séminaire

 

Some applications of the scaled Laplace transform inversion in Risk models

Robert Mnatsakanov, Department of Statistics, West Virginia University, Morgantown, USA

Abstract

In this talk we consider the problems of recovering the ultimate ruin probability and the compound distributions in the classical Poisson risk model. The uniform rate of approximations based on the finite values of the scaled Laplace transform are established. Questions about approximating the Expected Shrotfall and Value at Risk are discussed as well. Asymptotic behavior of proposed approximations and their empirical counterparts are illustrated by means of a simulation study.
Comparisons with other approximations based on the Maximum Entropy method and on a fixed Talbot algorithm are carried out via tables and plots in several typical examples.