B1458
Title: Calculating loss reserves for heavy-tailed insurance business
Authors: Colin Ramsay - University of Nebraska-Lincoln (United States) [presenting]
Annika Krutto - University of Oslo (Norway)
Abstract: Insurance losses from certain property/casualty lines of business are usually modelled as unimodal, heavy-tailed distributions. Commonly used loss models include the Pareto, lognormal, and Weibull distributions. However, few loss reserving techniques specifically deal with heavy-tailed individual losses, and, with a few exceptions, these methods assume the availability of sufficient loss data to detect claim settlement patterns or to estimate model parameters. A loss reserving method is developed based on the theory of the spacings of order statistics. Monte Carlo simulations are performed to check the accuracy of the method and compare it with some commonly used loss reserving methods, such as the classical chain ladder and the Bornhuetter Ferguson methods.
