Modelling actuarial data with a composite lognormal-Pareto model.(English)Zbl 1143.91027

The Pareto model covers the behaviour of large losses well, but fails to cover the behaviour of small losses. The lognormal model covers the behaviour of small losses well, but fails to cover the behaviour of large losses. In order to achieve both of these behaviours in one model the authors look for a desirable composite model, which took the two-parameter lognormal density up to an unknown threshold value and the two-parameter Pareto density for the rest of the model. The proposed composite density can be reparameterized and re-written as $f(x)=\begin{cases} {{\alpha\theta^{\alpha}}\over{(1+\Phi(k))x^{\alpha+1}}} \exp\left\{-{\alpha^{2}\over2k^2}\ln^{2}(x/\theta)\right\}& \text{if $$0<x\leq\theta$$}\\ {\alpha\theta^{\alpha}\over(1+\Phi(k))x^{\alpha+1}}& \text{if $$\theta\leq x<\infty$$},\end{cases}$ where $$\Phi(\cdot)$$ is the cumulative distribution function of the standard normal distribution and $$k$$ is a known constant which is given by the positive solution of the equation $$\exp(-k^2)=2\pi k^2$$. Properties and behaviour of composite lognormal-Pareto model are discussed. The authors study the maximum likelihood parameter estimation methods and related techniques for complete and censored data to the composite lognormal-Pareto model.

MSC:

 91B30 Risk theory, insurance (MSC2010)
Full Text:

References:

 [1] Klugman, S. A. and Panjer, H. H. and Willmot, G. E.(1998) Loss Models From Data to Decisions. New York : John Wiley & Sons, Inc.,. · Zbl 0905.62104 [2] Hogg, R. V. and Klugman, S. A.(1984) Loss Distributions. New York : John Wiley & Sons, Inc.. [3] Hossack, I. B. and Pollard, J. H. and Zehnwirth, B.(1983) Introductory Statistics with Applications in General Insurance. Cambridge University Press. · Zbl 0532.62080 [4] Beirlant, J. and Teugels, J. L. and Vynckier, P.(1996) Practical Analysis of Extreme Values. Belgium : Leuven University Press, Leuven. [5] Resnick, S. I. (1997) Discussion of the Danish Data on Large Fire Insurance Losses ASTIN Bulletin, 27, pp. 139 - 151. [6] Beirlant, J. and Joossens, E. and Segers, J. (2004) Generalized Pareto Fit to the Society of Actuaries’ Large Claims Database North American Actuarial Journal, 8(2), pp. 108 - 111. · Zbl 1085.62502 [7] McNeil, A. (1997) Estimating the Tails of Loss Severity Distributions using Extreme Value Theory ASTIN Bulletin, 27, pp. 117 - 137. [8] Patrik, G. (1980); Estimating Casualty Insurance Loss Amount Distributions, Proceedings of the Casualty Actuarial Society , Vol. LXVII, pp.57–109 [9] Ramlau-Hansen, H. (1988); A Solvency Study in Non-life Insurance. Part 1. Analyses of Fire, Windstrom, and Glass Claims, Scandinavian Actuarial Journal , 2, pp.3–34. [10] Embrechts, P. and Klüppelberg, C. and Mikosch, T.(1999) Modelling Extremal Events for Insurance and Finance. Berlin : Springer-Verlag. · Zbl 0873.62116
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.