Analysis of multispecies point patterns by using multivariate log-Gaussian Cox processes

Rasmus Waagepetersen, Yongtao Guan, Abdollah Jalilian, Jorge Mateu

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Multivariate log-Gaussian Cox processes are flexible models for multivariate point patterns. However, they have so far been applied in bivariate cases only. We move beyond the bivariate case to model multispecies point patterns of tree locations. In particular we address the problems of identifying parsimonious models and of extracting biologically relevant information from the models fitted. The latent multivariate Gaussian field is decomposed into components given in terms of random fields common to all species and components which are species specific. This allows a decomposition of variance that can be used to quantify to what extent the spatial variation of a species is governed by common or species-specific factors. Cross-validation is used to select the number of common latent fields to obtain a suitable trade-off between parsimony and fit of the data. The selected number of common latent fields provides an index of complexity of the multivariate covariance structure. Hierarchical clustering is used to identify groups of species with similar patterns of dependence on the common latent fields.

Original languageEnglish (US)
Pages (from-to)77-96
Number of pages20
JournalJournal of the Royal Statistical Society. Series C: Applied Statistics
Volume65
Issue number1
DOIs
StatePublished - Jan 1 2016

Fingerprint

Cox Process
Gaussian Process
Gaussian Fields
Parsimony
Covariance Structure
Hierarchical Clustering
Cross-validation
Model
Random Field
Quantify
Trade-offs
Cox process
Decompose

Keywords

  • Cross-correlation
  • Cross-validation
  • Hierarchical clustering
  • Log-Gaussian Cox process
  • Multivariate point process
  • Proportions of variance

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Analysis of multispecies point patterns by using multivariate log-Gaussian Cox processes. / Waagepetersen, Rasmus; Guan, Yongtao; Jalilian, Abdollah; Mateu, Jorge.

In: Journal of the Royal Statistical Society. Series C: Applied Statistics, Vol. 65, No. 1, 01.01.2016, p. 77-96.

Research output: Contribution to journalArticle

@article{ae0f82855793450b91456a0cd2f9b736,
title = "Analysis of multispecies point patterns by using multivariate log-Gaussian Cox processes",
abstract = "Multivariate log-Gaussian Cox processes are flexible models for multivariate point patterns. However, they have so far been applied in bivariate cases only. We move beyond the bivariate case to model multispecies point patterns of tree locations. In particular we address the problems of identifying parsimonious models and of extracting biologically relevant information from the models fitted. The latent multivariate Gaussian field is decomposed into components given in terms of random fields common to all species and components which are species specific. This allows a decomposition of variance that can be used to quantify to what extent the spatial variation of a species is governed by common or species-specific factors. Cross-validation is used to select the number of common latent fields to obtain a suitable trade-off between parsimony and fit of the data. The selected number of common latent fields provides an index of complexity of the multivariate covariance structure. Hierarchical clustering is used to identify groups of species with similar patterns of dependence on the common latent fields.",
keywords = "Cross-correlation, Cross-validation, Hierarchical clustering, Log-Gaussian Cox process, Multivariate point process, Proportions of variance",
author = "Rasmus Waagepetersen and Yongtao Guan and Abdollah Jalilian and Jorge Mateu",
year = "2016",
month = "1",
day = "1",
doi = "10.1111/rssc.12108",
language = "English (US)",
volume = "65",
pages = "77--96",
journal = "Journal of the Royal Statistical Society. Series C: Applied Statistics",
issn = "0035-9254",
publisher = "Wiley-Blackwell",
number = "1",

}

TY - JOUR

T1 - Analysis of multispecies point patterns by using multivariate log-Gaussian Cox processes

AU - Waagepetersen, Rasmus

AU - Guan, Yongtao

AU - Jalilian, Abdollah

AU - Mateu, Jorge

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Multivariate log-Gaussian Cox processes are flexible models for multivariate point patterns. However, they have so far been applied in bivariate cases only. We move beyond the bivariate case to model multispecies point patterns of tree locations. In particular we address the problems of identifying parsimonious models and of extracting biologically relevant information from the models fitted. The latent multivariate Gaussian field is decomposed into components given in terms of random fields common to all species and components which are species specific. This allows a decomposition of variance that can be used to quantify to what extent the spatial variation of a species is governed by common or species-specific factors. Cross-validation is used to select the number of common latent fields to obtain a suitable trade-off between parsimony and fit of the data. The selected number of common latent fields provides an index of complexity of the multivariate covariance structure. Hierarchical clustering is used to identify groups of species with similar patterns of dependence on the common latent fields.

AB - Multivariate log-Gaussian Cox processes are flexible models for multivariate point patterns. However, they have so far been applied in bivariate cases only. We move beyond the bivariate case to model multispecies point patterns of tree locations. In particular we address the problems of identifying parsimonious models and of extracting biologically relevant information from the models fitted. The latent multivariate Gaussian field is decomposed into components given in terms of random fields common to all species and components which are species specific. This allows a decomposition of variance that can be used to quantify to what extent the spatial variation of a species is governed by common or species-specific factors. Cross-validation is used to select the number of common latent fields to obtain a suitable trade-off between parsimony and fit of the data. The selected number of common latent fields provides an index of complexity of the multivariate covariance structure. Hierarchical clustering is used to identify groups of species with similar patterns of dependence on the common latent fields.

KW - Cross-correlation

KW - Cross-validation

KW - Hierarchical clustering

KW - Log-Gaussian Cox process

KW - Multivariate point process

KW - Proportions of variance

UR - http://www.scopus.com/inward/record.url?scp=84957802049&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957802049&partnerID=8YFLogxK

U2 - 10.1111/rssc.12108

DO - 10.1111/rssc.12108

M3 - Article

AN - SCOPUS:84957802049

VL - 65

SP - 77

EP - 96

JO - Journal of the Royal Statistical Society. Series C: Applied Statistics

JF - Journal of the Royal Statistical Society. Series C: Applied Statistics

SN - 0035-9254

IS - 1

ER -