On the occurrence times of componentwise maxima and bias in likelihood inference for multivariate max-stable distributions

Wadsworth, Jennifer (2015) On the occurrence times of componentwise maxima and bias in likelihood inference for multivariate max-stable distributions. Biometrika, 102 (3). pp. 705-711. ISSN 0006-3444

[img]
Preview
PDF (ArxivVersion2)
ArxivVersion2.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (248kB)

Abstract

Full likelihood-based inference for high-dimensional multivariate extreme value distributions, or max-stable processes, is feasible when incorporating occurrence times of the maxima; without this information, ddd-dimensional likelihood inference is usually precluded due to the large number of terms in the likelihood. However, some studies have noted bias when performing high-dimensional inference that incorporates such event information, particularly when dependence is weak. We elucidate this phenomenon, showing that for unbiased inference in moderate dimensions, dimension ddd should be of a magnitude smaller than the square root of the number of vectors over which one takes the componentwise maximum. A bias reduction technique is suggested and illustrated on the extreme-value logistic model.

Item Type:
Journal Article
Journal or Publication Title:
Biometrika
Additional Information:
This is a pre-copy-editing, author-produced PDF of an article accepted for publication in Biometrika following peer review. The definitive publisher-authenticated version Jennifer L. Wadsworth On the occurrence times of componentwise maxima and bias in likelihood inference for multivariate max-stable distributions Biometrika (2015) 102 (3): 705-711 first published online June 25, 2015 doi:10.1093/biomet/asv029 is available online at: http://biomet.oxfordjournals.org/content/102/3/705
Uncontrolled Keywords:
/dk/atira/pure/subjectarea/asjc/1100/1101
Subjects:
ID Code:
73953
Deposited By:
Deposited On:
18 Jun 2015 05:57
Refereed?:
Yes
Published?:
Published
Last Modified:
09 Jul 2020 03:45