An exponential–gamma mixture model for extreme Santa Ana winds

Gregory P. Bopp, Benjamin Adam Shaby

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We analyze the behavior of extreme winds occurring in Southern California during the Santa Ana wind season using a latent mixture model. This mixture representation is formulated as a hierarchical Bayesian model and fit using Markov chain Monte Carlo. The two-stage model results in generalized Pareto margins for exceedances and generates temporal dependence through a latent Markov process. This construction induces asymptotic independence in the response, while allowing for dependence at extreme, but subasymptotic, levels. We compare this model with a frequentist analogue where inference is performed via maximum pairwise likelihood. We use interval censoring to account for data quantization and estimate the extremal index and probabilities of multiday occurrences of extreme Santa Ana winds over a range of high thresholds.

Original languageEnglish (US)
Article numbere2476
JournalEnvironmetrics
Volume28
Issue number8
DOIs
StatePublished - Dec 1 2017

Fingerprint

Mixture Model
Extremes
Pairwise Likelihood
Extremal Index
Asymptotic Independence
Latent Process
Interval Censoring
Hierarchical Bayesian Model
Two-stage Model
Exceedance
Markov Chain Monte Carlo
Pareto
Markov Process
Margin
Maximum Likelihood
Quantization
Markov chain
Analogue
Estimate
Range of data

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Ecological Modeling

Cite this

Bopp, Gregory P. ; Shaby, Benjamin Adam. / An exponential–gamma mixture model for extreme Santa Ana winds. In: Environmetrics. 2017 ; Vol. 28, No. 8.
@article{d909c69cd8e642bb9b820f5e318ad6d3,
title = "An exponential–gamma mixture model for extreme Santa Ana winds",
abstract = "We analyze the behavior of extreme winds occurring in Southern California during the Santa Ana wind season using a latent mixture model. This mixture representation is formulated as a hierarchical Bayesian model and fit using Markov chain Monte Carlo. The two-stage model results in generalized Pareto margins for exceedances and generates temporal dependence through a latent Markov process. This construction induces asymptotic independence in the response, while allowing for dependence at extreme, but subasymptotic, levels. We compare this model with a frequentist analogue where inference is performed via maximum pairwise likelihood. We use interval censoring to account for data quantization and estimate the extremal index and probabilities of multiday occurrences of extreme Santa Ana winds over a range of high thresholds.",
author = "Bopp, {Gregory P.} and Shaby, {Benjamin Adam}",
year = "2017",
month = "12",
day = "1",
doi = "10.1002/env.2476",
language = "English (US)",
volume = "28",
journal = "Environmetrics",
issn = "1180-4009",
publisher = "John Wiley and Sons Ltd",
number = "8",

}

An exponential–gamma mixture model for extreme Santa Ana winds. / Bopp, Gregory P.; Shaby, Benjamin Adam.

In: Environmetrics, Vol. 28, No. 8, e2476, 01.12.2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An exponential–gamma mixture model for extreme Santa Ana winds

AU - Bopp, Gregory P.

AU - Shaby, Benjamin Adam

PY - 2017/12/1

Y1 - 2017/12/1

N2 - We analyze the behavior of extreme winds occurring in Southern California during the Santa Ana wind season using a latent mixture model. This mixture representation is formulated as a hierarchical Bayesian model and fit using Markov chain Monte Carlo. The two-stage model results in generalized Pareto margins for exceedances and generates temporal dependence through a latent Markov process. This construction induces asymptotic independence in the response, while allowing for dependence at extreme, but subasymptotic, levels. We compare this model with a frequentist analogue where inference is performed via maximum pairwise likelihood. We use interval censoring to account for data quantization and estimate the extremal index and probabilities of multiday occurrences of extreme Santa Ana winds over a range of high thresholds.

AB - We analyze the behavior of extreme winds occurring in Southern California during the Santa Ana wind season using a latent mixture model. This mixture representation is formulated as a hierarchical Bayesian model and fit using Markov chain Monte Carlo. The two-stage model results in generalized Pareto margins for exceedances and generates temporal dependence through a latent Markov process. This construction induces asymptotic independence in the response, while allowing for dependence at extreme, but subasymptotic, levels. We compare this model with a frequentist analogue where inference is performed via maximum pairwise likelihood. We use interval censoring to account for data quantization and estimate the extremal index and probabilities of multiday occurrences of extreme Santa Ana winds over a range of high thresholds.

UR - http://www.scopus.com/inward/record.url?scp=85029395268&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029395268&partnerID=8YFLogxK

U2 - 10.1002/env.2476

DO - 10.1002/env.2476

M3 - Article

AN - SCOPUS:85029395268

VL - 28

JO - Environmetrics

JF - Environmetrics

SN - 1180-4009

IS - 8

M1 - e2476

ER -