On the likelihood function of Gaussian max-stable processes

Marc Genton; Yanyuan Ma; Huiyan Sang

doi:10.1093/biomet/asr020

On the likelihood function of Gaussian max-stable processes

Marc Genton, Yanyuan Ma, Huiyan Sang

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

75 Scopus citations

Abstract

We derive a closed form expression for the likelihood function of a Gaussian max-stable process indexed by ℝ^d at p≤d+1 sites, d≥1. We demonstrate the gain in efficiency in the maximum composite likelihood estimators of the covariance matrix from p=2 to p=3 sites in ℝ² by means of a Monte Carlo simulation study.

Original language	English (US)
Pages (from-to)	481-488
Number of pages	8
Journal	Biometrika
Volume	98
Issue number	2
DOIs	https://doi.org/10.1093/biomet/asr020
State	Published - Jun 2011
Externally published	Yes

Keywords

Composite likelihood
Extreme event
Multivariate index
Pairwise and triplewise inference
Spatial statistics

ASJC Scopus subject areas

Applied Mathematics
Agricultural and Biological Sciences (miscellaneous)
General Agricultural and Biological Sciences
Statistics and Probability
Statistics, Probability and Uncertainty
General Mathematics

Access to Document

10.1093/biomet/asr020

Cite this

@article{9b13ad40f86f4c3f850c3ae44068c9b3,

title = "On the likelihood function of Gaussian max-stable processes",

abstract = "We derive a closed form expression for the likelihood function of a Gaussian max-stable process indexed by ℝd at p≤d+1 sites, d≥1. We demonstrate the gain in efficiency in the maximum composite likelihood estimators of the covariance matrix from p=2 to p=3 sites in ℝ2 by means of a Monte Carlo simulation study.",

keywords = "Composite likelihood, Extreme event, Multivariate index, Pairwise and triplewise inference, Spatial statistics",

author = "Marc Genton and Yanyuan Ma and Huiyan Sang",

note = "KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: This research was sponsored by the U.S. National Science Foundation and by an award made by KingAbdullah University of Science and Technology. The authors thank the editor and two referees for veryuseful comments. This publication acknowledges KAUST support, but has no KAUST affiliated authors.",

year = "2011",

month = jun,

doi = "10.1093/biomet/asr020",

language = "English (US)",

volume = "98",

pages = "481--488",

journal = "Biometrika",

issn = "0006-3444",

publisher = "Oxford University Press",

number = "2",

}

TY - JOUR

T1 - On the likelihood function of Gaussian max-stable processes

AU - Genton, Marc

AU - Ma, Yanyuan

AU - Sang, Huiyan

N1 - KAUST Repository Item: Exported on 2020-10-01 Acknowledgements: This research was sponsored by the U.S. National Science Foundation and by an award made by KingAbdullah University of Science and Technology. The authors thank the editor and two referees for veryuseful comments. This publication acknowledges KAUST support, but has no KAUST affiliated authors.

PY - 2011/6

Y1 - 2011/6

N2 - We derive a closed form expression for the likelihood function of a Gaussian max-stable process indexed by ℝd at p≤d+1 sites, d≥1. We demonstrate the gain in efficiency in the maximum composite likelihood estimators of the covariance matrix from p=2 to p=3 sites in ℝ2 by means of a Monte Carlo simulation study.

AB - We derive a closed form expression for the likelihood function of a Gaussian max-stable process indexed by ℝd at p≤d+1 sites, d≥1. We demonstrate the gain in efficiency in the maximum composite likelihood estimators of the covariance matrix from p=2 to p=3 sites in ℝ2 by means of a Monte Carlo simulation study.

KW - Composite likelihood

KW - Extreme event

KW - Multivariate index

KW - Pairwise and triplewise inference

KW - Spatial statistics

UR - http://www.scopus.com/inward/record.url?scp=79957814400&partnerID=8YFLogxK

U2 - 10.1093/biomet/asr020

DO - 10.1093/biomet/asr020

M3 - Article

AN - SCOPUS:79957814400

SN - 0006-3444

VL - 98

SP - 481

EP - 488

JO - Biometrika

JF - Biometrika

IS - 2

ER -

On the likelihood function of Gaussian max-stable processes

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this