Fitting phase--type scale mixtures to heavy--tailed data and distributions

Bladt, M and Rojas-Nandayapa, L (2017) Fitting phase--type scale mixtures to heavy--tailed data and distributions. Extremes: statistical theory and applications in science, engineering and economics. ISSN 1386-1999

Text 1705.04357v1.pdf - Submitted version Download (1MB)

Abstract

We consider the fitting of heavy tailed data and distribution with a special attention to distributions with a non--standard shape in the "body" of the distribution. To this end we consider a dense class of heavy tailed distributions introduced recently, employing an EM algorithm for the the maximum likelihood estimates of its parameters. We present methods for fitting to observed data, histograms, censored data, as well as to theoretical distributions. Numerical examples are provided with simulated data and a benchmark reinsurance dataset. We empirically demonstrate that our model can provide excellent fits to heavy--tailed data/distributions with minimal assumptions

Item Type:	Article
Uncontrolled Keywords:	math.ST, math.ST, stat.TH
Depositing User:	Symplectic Admin
Date Deposited:	24 May 2017 08:52
Last Modified:	19 Jan 2023 07:04
DOI:	10.1007/s10687-017-0306-4
Related URLs:	http://arxiv.org/abs/1705.04357v1
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3007614

Available Versions of this Item

• Fitting phase--type scale mixtures to heavy--tailed data and distributions. (deposited 24 May 2017 08:52) [Currently Displayed]
  • Fitting phase--type scale mixtures to heavy--tailed data and distributions. (deposited 11 Dec 2017 08:44)