A Poisson process reparameterisation for Bayesian inference for extremes

Sharkey, Paul and Tawn, Jonathan Angus (2017) A Poisson process reparameterisation for Bayesian inference for extremes. Extremes, 20 (2). pp. 239-263. ISSN 1386-1999

[img]
Preview
PDF (pppaper_revision1)
pppaper_revision1.pdf - Accepted Version
Available under License Creative Commons Attribution-NoDerivs.

Download (2MB)

Abstract

A common approach to modelling extreme values is to consider the excesses above a high threshold as realisations of a non-homogeneous Poisson process. While this method offers the advantage of modelling using threshold-invariant extreme value parameters, the dependence between these parameters makes estimation more dicult. We present a novel approach for Bayesian estimation of the Poisson process model parameters by reparameterising in terms of a tuning parameter m. This paper presents a method for choosing the optimal value of m that near-orthogonalises the parameters, which is achieved by minimising the correlation between the asymptotic posterior distribution of the parameters. This choice of m ensures more rapid convergence and ecient sampling from the joint posterior distribution using Markov Chain Monte Carlo methods. Samples from the parameterisation of interest are then obtained by a simple transform. Results are presented in the cases of identically and non-identically distributed models for extreme rainfall in Cumbria, UK.

Item Type:
Journal Article
Journal or Publication Title:
Extremes
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/2600/2613
Subjects:
ID Code:
84835
Deposited By:
Deposited On:
23 Feb 2017 13:44
Refereed?:
Yes
Published?:
Published
Last Modified:
25 Sep 2020 03:00