Exploiting structure of maximum likelihood estimators for extreme value threshold selection

Wadsworth, Jennifer (2016) Exploiting structure of maximum likelihood estimators for extreme value threshold selection. Technometrics, 58 (1). pp. 116-126. ISSN 0040-1706

[thumbnail of MLEStructure]
Preview
PDF (MLEStructure)
MLEStructure.pdf - Accepted Version
Available under License Creative Commons Attribution-NonCommercial.

Download (628kB)

Abstract

In order to model the tail of a distribution, one has to define the threshold above or below which an extreme value model produces a suitable fit. Parameter stability plots, whereby one plots maximum likelihood estimates of supposedly threshold-independent parameters against threshold, form one of the main tools for threshold selection by practitioners, principally due to their simplicity. However, one repeated criticism of these plots is their lack of interpretability, with pointwise confidence intervals being strongly dependent across the range of thresholds. In this article, we exploit the independent-increments structure of maximum likelihood estimators in order to produce complementary plots with greater interpretability, and a suggest simple likelihood-based procedure which allows for automated threshold selection.

Item Type:
Journal Article
Journal or Publication Title:
Technometrics
Additional Information:
The final, definitive version of this article has been published in the Journal, Technometrics, 58 (1), 2016, © Informa Plc
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/2600/2611
Subjects:
?? diagnostic plotsextreme value modellingmaximum likelihoodthreshold selectionmodelling and simulationapplied mathematicsstatistics and probability ??
ID Code:
73952
Deposited By:
Deposited On:
18 Jun 2015 05:57
Refereed?:
Yes
Published?:
Published
Last Modified:
18 Nov 2024 01:11