Structured Spatio-temporal shot-noise Cox point process models, with a view to modelling forest fires

Jesper Møller, Carlos Diaz-Avalos

Research output: Contribution to journalJournal articleResearchpeer-review

28 Citations (Scopus)

Abstract

Spatio-temporal Cox point process models with a multiplicative structure for the driving random intensity, incorporating covariate information into temporal and spatial components, and with a residual term modelled by a shot-noise process, are considered. Such models are flexible and tractable for statistical analysis, using spatio-temporal versions of intensity and inhomogeneous K-functions, quick estimation procedures based on composite likelihoods and minimum contrast estimation, and easy simulation techniques. These advantages are demonstrated in connection with the analysis of a relatively large data set consisting of 2796 days and 5834 spatial locations of fires. The model is compared with a spatio-temporal log-Gaussian Cox point process model, and likelihood-based methods are discussed to some extent.
Original languageEnglish
JournalScandinavian Journal of Statistics
Volume37
Issue number1
Pages (from-to)2-25
Number of pages24
ISSN0303-6898
DOIs
Publication statusPublished - 2010

Fingerprint

Cox Process
Forest Fire
Shot Noise
Point Process
Process Model
Shot Noise Process
Modeling
Composite Likelihood
Large Data Sets
Statistical Analysis
Covariates
Likelihood
Multiplicative
Term
Model
Process model
Point process
Forest fire
Simulation

Cite this

@article{361339a0ea2611deb63d000ea68e967b,
title = "Structured Spatio-temporal shot-noise Cox point process models, with a view to modelling forest fires",
abstract = "Spatio-temporal Cox point process models with a multiplicative structure for the driving random intensity, incorporating covariate information into temporal and spatial components, and with a residual term modelled by a shot-noise process, are considered. Such models are flexible and tractable for statistical analysis, using spatio-temporal versions of intensity and inhomogeneous K-functions, quick estimation procedures based on composite likelihoods and minimum contrast estimation, and easy simulation techniques. These advantages are demonstrated in connection with the analysis of a relatively large data set consisting of 2796 days and 5834 spatial locations of fires. The model is compared with a spatio-temporal log-Gaussian Cox point process model, and likelihood-based methods are discussed to some extent.",
author = "Jesper M{\o}ller and Carlos Diaz-Avalos",
year = "2010",
doi = "10.1111/j.1467-9469.2009.00670.x",
language = "English",
volume = "37",
pages = "2--25",
journal = "Scandinavian Journal of Statistics",
issn = "0303-6898",
publisher = "Wiley-Blackwell",
number = "1",

}

Structured Spatio-temporal shot-noise Cox point process models, with a view to modelling forest fires. / Møller, Jesper; Diaz-Avalos, Carlos.

In: Scandinavian Journal of Statistics, Vol. 37, No. 1, 2010, p. 2-25.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Structured Spatio-temporal shot-noise Cox point process models, with a view to modelling forest fires

AU - Møller, Jesper

AU - Diaz-Avalos, Carlos

PY - 2010

Y1 - 2010

N2 - Spatio-temporal Cox point process models with a multiplicative structure for the driving random intensity, incorporating covariate information into temporal and spatial components, and with a residual term modelled by a shot-noise process, are considered. Such models are flexible and tractable for statistical analysis, using spatio-temporal versions of intensity and inhomogeneous K-functions, quick estimation procedures based on composite likelihoods and minimum contrast estimation, and easy simulation techniques. These advantages are demonstrated in connection with the analysis of a relatively large data set consisting of 2796 days and 5834 spatial locations of fires. The model is compared with a spatio-temporal log-Gaussian Cox point process model, and likelihood-based methods are discussed to some extent.

AB - Spatio-temporal Cox point process models with a multiplicative structure for the driving random intensity, incorporating covariate information into temporal and spatial components, and with a residual term modelled by a shot-noise process, are considered. Such models are flexible and tractable for statistical analysis, using spatio-temporal versions of intensity and inhomogeneous K-functions, quick estimation procedures based on composite likelihoods and minimum contrast estimation, and easy simulation techniques. These advantages are demonstrated in connection with the analysis of a relatively large data set consisting of 2796 days and 5834 spatial locations of fires. The model is compared with a spatio-temporal log-Gaussian Cox point process model, and likelihood-based methods are discussed to some extent.

U2 - 10.1111/j.1467-9469.2009.00670.x

DO - 10.1111/j.1467-9469.2009.00670.x

M3 - Journal article

VL - 37

SP - 2

EP - 25

JO - Scandinavian Journal of Statistics

JF - Scandinavian Journal of Statistics

SN - 0303-6898

IS - 1

ER -