A hierarchical max-stable spatial model for extreme precipitation

Brian J. Reich, Benjamin Adam Shaby

Research output: Contribution to journalArticle

64 Citations (Scopus)

Abstract

Extreme environmental phenomena such as major precipitation events manifestly exhibit spatial dependence. Max-stable processes are a class of asymptotically-justified models that are capable of representing spatial dependence among extreme values. While these models satisfy modeling requirements, they are limited in their utility because their corresponding joint likelihoods are unknown for more than a trivial number of spatial locations, preventing, in particular, Bayesian analyses. In this paper, we propose a new random effects model to account for spatial dependence. We show that our specification of the random effect distribution leads to a max-stable process that has the popular Gaussian extreme value process (GEVP) as a limiting case. The proposed model is used to analyze the yearly maximum precipitation from a regional climate model.

Original languageEnglish (US)
Pages (from-to)1430-1451
Number of pages22
JournalAnnals of Applied Statistics
Volume6
Issue number4
DOIs
StatePublished - Jan 1 2012

Fingerprint

Spatial Dependence
Stable Models
Spatial Model
Extremes
Stable Process
Extreme Values
Climate Models
Random Effects Model
Random Effects
Climate models
Likelihood
Trivial
Limiting
Model
Specification
Unknown
Requirements
Specifications
Modeling
Spatial model

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Modeling and Simulation
  • Statistics, Probability and Uncertainty

Cite this

Reich, Brian J. ; Shaby, Benjamin Adam. / A hierarchical max-stable spatial model for extreme precipitation. In: Annals of Applied Statistics. 2012 ; Vol. 6, No. 4. pp. 1430-1451.
@article{4a96803c84764f07821e5a33f082c873,
title = "A hierarchical max-stable spatial model for extreme precipitation",
abstract = "Extreme environmental phenomena such as major precipitation events manifestly exhibit spatial dependence. Max-stable processes are a class of asymptotically-justified models that are capable of representing spatial dependence among extreme values. While these models satisfy modeling requirements, they are limited in their utility because their corresponding joint likelihoods are unknown for more than a trivial number of spatial locations, preventing, in particular, Bayesian analyses. In this paper, we propose a new random effects model to account for spatial dependence. We show that our specification of the random effect distribution leads to a max-stable process that has the popular Gaussian extreme value process (GEVP) as a limiting case. The proposed model is used to analyze the yearly maximum precipitation from a regional climate model.",
author = "Reich, {Brian J.} and Shaby, {Benjamin Adam}",
year = "2012",
month = "1",
day = "1",
doi = "10.1214/12-AOAS591",
language = "English (US)",
volume = "6",
pages = "1430--1451",
journal = "Annals of Applied Statistics",
issn = "1932-6157",
publisher = "Institute of Mathematical Statistics",
number = "4",

}

A hierarchical max-stable spatial model for extreme precipitation. / Reich, Brian J.; Shaby, Benjamin Adam.

In: Annals of Applied Statistics, Vol. 6, No. 4, 01.01.2012, p. 1430-1451.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A hierarchical max-stable spatial model for extreme precipitation

AU - Reich, Brian J.

AU - Shaby, Benjamin Adam

PY - 2012/1/1

Y1 - 2012/1/1

N2 - Extreme environmental phenomena such as major precipitation events manifestly exhibit spatial dependence. Max-stable processes are a class of asymptotically-justified models that are capable of representing spatial dependence among extreme values. While these models satisfy modeling requirements, they are limited in their utility because their corresponding joint likelihoods are unknown for more than a trivial number of spatial locations, preventing, in particular, Bayesian analyses. In this paper, we propose a new random effects model to account for spatial dependence. We show that our specification of the random effect distribution leads to a max-stable process that has the popular Gaussian extreme value process (GEVP) as a limiting case. The proposed model is used to analyze the yearly maximum precipitation from a regional climate model.

AB - Extreme environmental phenomena such as major precipitation events manifestly exhibit spatial dependence. Max-stable processes are a class of asymptotically-justified models that are capable of representing spatial dependence among extreme values. While these models satisfy modeling requirements, they are limited in their utility because their corresponding joint likelihoods are unknown for more than a trivial number of spatial locations, preventing, in particular, Bayesian analyses. In this paper, we propose a new random effects model to account for spatial dependence. We show that our specification of the random effect distribution leads to a max-stable process that has the popular Gaussian extreme value process (GEVP) as a limiting case. The proposed model is used to analyze the yearly maximum precipitation from a regional climate model.

UR - http://www.scopus.com/inward/record.url?scp=84871710529&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84871710529&partnerID=8YFLogxK

U2 - 10.1214/12-AOAS591

DO - 10.1214/12-AOAS591

M3 - Article

C2 - 23795226

AN - SCOPUS:84871710529

VL - 6

SP - 1430

EP - 1451

JO - Annals of Applied Statistics

JF - Annals of Applied Statistics

SN - 1932-6157

IS - 4

ER -