When does the mean excess plot look linear?
Statistics Theory
2010-12-01 v1 Probability
Statistics Theory
Abstract
In risk analysis, the mean excess plot is a commonly used exploratory plotting technique for confirming iid data is consistent with a generalized Pareto assumption for the underlying distribution, since in the presence of such a distribution thresholded data have a mean excess plot that is roughly linear. Does any other class of distributions share this linearity of the plot? Under some extra assumptions, we are able to conclude that only the generalized Pareto family has this property.
Cite
@article{arxiv.1011.6447,
title = {When does the mean excess plot look linear?},
author = {Souvik Ghosh and Sidney I. Resnick},
journal= {arXiv preprint arXiv:1011.6447},
year = {2010}
}
Comments
14 pages