Full likelihood inference for max-stable data

Raphaël Huser; Clément Dombry; Mathieu Ribatet; Marc G. Genton

doi:10.1002/sta4.218

Full likelihood inference for max-stable data

Raphaël Huser, Clément Dombry, Mathieu Ribatet, Marc G. Genton

Research output: Contribution to journal › Article › peer-review

31 Scopus citations

Abstract

We show how to perform full likelihood inference for max-stable multivariate distributions or processes based on a stochastic expectation–maximization algorithm, which combines statistical and computational efficiency in high dimensions. The good performance of this methodology is demonstrated by simulation based on the popular logistic and Brown–Resnick models, and it is shown to provide computational time improvements with respect to a direct computation of the likelihood. Strategies to further reduce the computational burden are also discussed.

Original language	English (US)
Journal	Stat
Volume	8
Issue number	1
DOIs	https://doi.org/10.1002/sta4.218
State	Published - Jan 28 2019

Bibliographical note

KAUST Repository Item: Exported on 2020-04-23
Acknowledgements: This research was supported by King Abdullah University of Science and Technology (KAUST). This research made use of the resources of the KAUST Supercomputing Laboratory.

Access to Document

10.1002/sta4.218

Cite this

@article{ebc27d7e3d3f4e24822ba80d392a53ac,

title = "Full likelihood inference for max-stable data",

abstract = "We show how to perform full likelihood inference for max-stable multivariate distributions or processes based on a stochastic expectation–maximization algorithm, which combines statistical and computational efficiency in high dimensions. The good performance of this methodology is demonstrated by simulation based on the popular logistic and Brown–Resnick models, and it is shown to provide computational time improvements with respect to a direct computation of the likelihood. Strategies to further reduce the computational burden are also discussed.",

author = "Rapha{\"e}l Huser and Cl{\'e}ment Dombry and Mathieu Ribatet and Genton, {Marc G.}",

note = "KAUST Repository Item: Exported on 2020-04-23 Acknowledgements: This research was supported by King Abdullah University of Science and Technology (KAUST). This research made use of the resources of the KAUST Supercomputing Laboratory.",

year = "2019",

month = jan,

day = "28",

doi = "10.1002/sta4.218",

language = "English (US)",

volume = "8",

journal = "Stat",

issn = "2049-1573",

publisher = "Wisconsin Nurses Association",

number = "1",

}

TY - JOUR

T1 - Full likelihood inference for max-stable data

AU - Huser, Raphaël

AU - Dombry, Clément

AU - Ribatet, Mathieu

AU - Genton, Marc G.

N1 - KAUST Repository Item: Exported on 2020-04-23 Acknowledgements: This research was supported by King Abdullah University of Science and Technology (KAUST). This research made use of the resources of the KAUST Supercomputing Laboratory.

PY - 2019/1/28

Y1 - 2019/1/28

N2 - We show how to perform full likelihood inference for max-stable multivariate distributions or processes based on a stochastic expectation–maximization algorithm, which combines statistical and computational efficiency in high dimensions. The good performance of this methodology is demonstrated by simulation based on the popular logistic and Brown–Resnick models, and it is shown to provide computational time improvements with respect to a direct computation of the likelihood. Strategies to further reduce the computational burden are also discussed.

AB - We show how to perform full likelihood inference for max-stable multivariate distributions or processes based on a stochastic expectation–maximization algorithm, which combines statistical and computational efficiency in high dimensions. The good performance of this methodology is demonstrated by simulation based on the popular logistic and Brown–Resnick models, and it is shown to provide computational time improvements with respect to a direct computation of the likelihood. Strategies to further reduce the computational burden are also discussed.

UR - http://hdl.handle.net/10754/630973

UR - https://onlinelibrary.wiley.com/doi/full/10.1002/sta4.218

UR - http://www.scopus.com/inward/record.url?scp=85064481477&partnerID=8YFLogxK

U2 - 10.1002/sta4.218

DO - 10.1002/sta4.218

M3 - Article

SN - 2049-1573

VL - 8

JO - Stat

JF - Stat

IS - 1

ER -

Full likelihood inference for max-stable data

Abstract

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this