Home > Research > Publications & Outputs > Advances in Statistical Modeling of Spatial Ext...

Electronic data

  • FinalSubmittedVersion

    Accepted author manuscript, 2.52 MB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Advances in Statistical Modeling of Spatial Extremes

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Advances in Statistical Modeling of Spatial Extremes. / Huser, Raphael; Wadsworth, Jennifer.

In: WIREs Computational Statistics, Vol. 14, No. 1, e1537, 31.01.2022.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Huser, R & Wadsworth, J 2022, 'Advances in Statistical Modeling of Spatial Extremes', WIREs Computational Statistics, vol. 14, no. 1, e1537. https://doi.org/10.1002/wics.1537

APA

Huser, R., & Wadsworth, J. (2022). Advances in Statistical Modeling of Spatial Extremes. WIREs Computational Statistics, 14(1), [e1537]. https://doi.org/10.1002/wics.1537

Vancouver

Huser R, Wadsworth J. Advances in Statistical Modeling of Spatial Extremes. WIREs Computational Statistics. 2022 Jan 31;14(1):e1537. Epub 2020 Nov 20. doi: 10.1002/wics.1537

Author

Huser, Raphael ; Wadsworth, Jennifer. / Advances in Statistical Modeling of Spatial Extremes. In: WIREs Computational Statistics. 2022 ; Vol. 14, No. 1.

Bibtex

@article{bd32f0fdbcbd49ef8449258a713f3dc2,
title = "Advances in Statistical Modeling of Spatial Extremes",
abstract = "The classical modeling of spatial extremes relies on asymptotic models (i.e., max‐stable or r‐Pareto processes) for block maxima or peaks over high thresholds, respectively. However, at finite levels, empirical evidence often suggests that such asymptotic models are too rigidly constrained, and that they do not adequately capture the frequent situation where more severe events tend to be spatially more localized. In other words, these asymptotic models have a strong tail dependence that persists at increasingly high levels, while data usually suggest that it should weaken instead. Another well‐known limitation of classical spatial extremes models is that they are either computationally prohibitive to fit in high dimensions, or they need to be fitted using less efficient techniques. In this review paper, we describe recent progress in the modeling and inference for spatial extremes, focusing on new models that have more flexible tail structures that can bridge asymptotic dependence classes, and that are more easily amenable to likelihood‐based inference for large datasets. In particular, we discuss various types of random scale constructions, as well as the conditional spatial extremes model, which have recently been getting increasing attention within the statistics of extremes community. We illustrate some of these new spatial models on two different environmental applications.",
keywords = "Asymptotic dependence and independence, Extreme-value theory, Max-stable process, Pareto process, Random scale mixture",
author = "Raphael Huser and Jennifer Wadsworth",
year = "2022",
month = jan,
day = "31",
doi = "10.1002/wics.1537",
language = "English",
volume = "14",
journal = "WIREs Computational Statistics",
issn = "1939-0068",
publisher = "John Wiley and Sons Inc.",
number = "1",

}

RIS

TY - JOUR

T1 - Advances in Statistical Modeling of Spatial Extremes

AU - Huser, Raphael

AU - Wadsworth, Jennifer

PY - 2022/1/31

Y1 - 2022/1/31

N2 - The classical modeling of spatial extremes relies on asymptotic models (i.e., max‐stable or r‐Pareto processes) for block maxima or peaks over high thresholds, respectively. However, at finite levels, empirical evidence often suggests that such asymptotic models are too rigidly constrained, and that they do not adequately capture the frequent situation where more severe events tend to be spatially more localized. In other words, these asymptotic models have a strong tail dependence that persists at increasingly high levels, while data usually suggest that it should weaken instead. Another well‐known limitation of classical spatial extremes models is that they are either computationally prohibitive to fit in high dimensions, or they need to be fitted using less efficient techniques. In this review paper, we describe recent progress in the modeling and inference for spatial extremes, focusing on new models that have more flexible tail structures that can bridge asymptotic dependence classes, and that are more easily amenable to likelihood‐based inference for large datasets. In particular, we discuss various types of random scale constructions, as well as the conditional spatial extremes model, which have recently been getting increasing attention within the statistics of extremes community. We illustrate some of these new spatial models on two different environmental applications.

AB - The classical modeling of spatial extremes relies on asymptotic models (i.e., max‐stable or r‐Pareto processes) for block maxima or peaks over high thresholds, respectively. However, at finite levels, empirical evidence often suggests that such asymptotic models are too rigidly constrained, and that they do not adequately capture the frequent situation where more severe events tend to be spatially more localized. In other words, these asymptotic models have a strong tail dependence that persists at increasingly high levels, while data usually suggest that it should weaken instead. Another well‐known limitation of classical spatial extremes models is that they are either computationally prohibitive to fit in high dimensions, or they need to be fitted using less efficient techniques. In this review paper, we describe recent progress in the modeling and inference for spatial extremes, focusing on new models that have more flexible tail structures that can bridge asymptotic dependence classes, and that are more easily amenable to likelihood‐based inference for large datasets. In particular, we discuss various types of random scale constructions, as well as the conditional spatial extremes model, which have recently been getting increasing attention within the statistics of extremes community. We illustrate some of these new spatial models on two different environmental applications.

KW - Asymptotic dependence and independence

KW - Extreme-value theory

KW - Max-stable process

KW - Pareto process

KW - Random scale mixture

U2 - 10.1002/wics.1537

DO - 10.1002/wics.1537

M3 - Journal article

VL - 14

JO - WIREs Computational Statistics

JF - WIREs Computational Statistics

SN - 1939-0068

IS - 1

M1 - e1537

ER -