Composite Lognormal-Pareto model with random threshold
(2010) , 18 pages
Files
DP1014.pdf
Open Access - Adobe PDF
- 321.55 KB
Details
- Authors
- Abstract
- This paper further considers the composite Lognormal-Pareto model proposed by Cooray & Ananda (2005) and suitably modified by Scollnik (2007). This model is based on a Lognormal density up to an unknown threshold value and a Pareto density thereafter. Instead of using a single threshold value applying uniformly to the whole data set, the model proposed in the present paper allows for heterogeneity with respect to the threshold and let it vary among observations. Specifically, the threshold value for a particular observation is seen as the realization of a positive random variable and the mixed composite Lognormal- Pareto model is obtained by averaging over the population of interest. The performance of the composite Lognormal-Pareto model and of its mixed extension is compared using the well-known Danish fire losses data set.
- Affiliations
Citations
Pigeon, M., & Denuit, M. (2010). Composite Lognormal-Pareto model with random threshold (ISBA Discussion Paper 1014). https://hdl.handle.net/2078.5/207938