A comparison of joint species distribution models for presence–absence data

David P. Wilkinson, Nick Golding, Gurutzeta Guillera-Arroita, Reid Tingley, Michael A. McCarthy

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Joint species distribution models (JSDMs) account for biotic interactions and missing environmental predictors in correlative species distribution models. Several different JSDMs have been proposed in the literature, but the use of different or conflicting nomenclature and statistical notation potentially obscures similarities and differences among them. Furthermore, new JSDM implementations have been illustrated with different case studies, preventing direct comparisons of computational and statistical performance. We aim to resolve these outstanding issues by (a) highlighting similarities among seven presence–absence JSDMs using a clearly defined, singular notation; and (b) evaluating the computational and statistical performance of each JSDM using six datasets that vary widely in numbers of sites, species, and environmental covariates considered. Our singular notation shows that many of the JSDMs are very similar, and in turn parameter estimates of different JSDMs are moderate to strongly, positively correlated. In contrast, the different JSDMs clearly differ in computational efficiency and memory limitations. Our framework will allow ecologists to make educated decisions about the JSDM that best suits their objective, and enable wider uptake of JSDM methods among the ecological community.

Original languageEnglish
Pages (from-to)198-211
Number of pages14
JournalMethods in Ecology and Evolution
Volume10
Issue number2
DOIs
Publication statusPublished - Feb 2019
Externally publishedYes

Keywords

  • biotic interactions
  • community assembly
  • hierarchical models
  • joint species distribution model
  • latent factors
  • presence–absence
  • residual correlation

Cite this

Wilkinson, David P. ; Golding, Nick ; Guillera-Arroita, Gurutzeta ; Tingley, Reid ; McCarthy, Michael A. / A comparison of joint species distribution models for presence–absence data. In: Methods in Ecology and Evolution. 2019 ; Vol. 10, No. 2. pp. 198-211.
@article{4df53637d79c4ac8ae746d0dff41b030,
title = "A comparison of joint species distribution models for presence–absence data",
abstract = "Joint species distribution models (JSDMs) account for biotic interactions and missing environmental predictors in correlative species distribution models. Several different JSDMs have been proposed in the literature, but the use of different or conflicting nomenclature and statistical notation potentially obscures similarities and differences among them. Furthermore, new JSDM implementations have been illustrated with different case studies, preventing direct comparisons of computational and statistical performance. We aim to resolve these outstanding issues by (a) highlighting similarities among seven presence–absence JSDMs using a clearly defined, singular notation; and (b) evaluating the computational and statistical performance of each JSDM using six datasets that vary widely in numbers of sites, species, and environmental covariates considered. Our singular notation shows that many of the JSDMs are very similar, and in turn parameter estimates of different JSDMs are moderate to strongly, positively correlated. In contrast, the different JSDMs clearly differ in computational efficiency and memory limitations. Our framework will allow ecologists to make educated decisions about the JSDM that best suits their objective, and enable wider uptake of JSDM methods among the ecological community.",
keywords = "biotic interactions, community assembly, hierarchical models, joint species distribution model, latent factors, presence–absence, residual correlation",
author = "Wilkinson, {David P.} and Nick Golding and Gurutzeta Guillera-Arroita and Reid Tingley and McCarthy, {Michael A.}",
year = "2019",
month = "2",
doi = "10.1111/2041-210X.13106",
language = "English",
volume = "10",
pages = "198--211",
journal = "Methods in Ecology and Evolution",
issn = "2041-210X",
publisher = "Wiley-Blackwell",
number = "2",

}

A comparison of joint species distribution models for presence–absence data. / Wilkinson, David P.; Golding, Nick; Guillera-Arroita, Gurutzeta; Tingley, Reid; McCarthy, Michael A.

In: Methods in Ecology and Evolution, Vol. 10, No. 2, 02.2019, p. 198-211.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A comparison of joint species distribution models for presence–absence data

AU - Wilkinson, David P.

AU - Golding, Nick

AU - Guillera-Arroita, Gurutzeta

AU - Tingley, Reid

AU - McCarthy, Michael A.

PY - 2019/2

Y1 - 2019/2

N2 - Joint species distribution models (JSDMs) account for biotic interactions and missing environmental predictors in correlative species distribution models. Several different JSDMs have been proposed in the literature, but the use of different or conflicting nomenclature and statistical notation potentially obscures similarities and differences among them. Furthermore, new JSDM implementations have been illustrated with different case studies, preventing direct comparisons of computational and statistical performance. We aim to resolve these outstanding issues by (a) highlighting similarities among seven presence–absence JSDMs using a clearly defined, singular notation; and (b) evaluating the computational and statistical performance of each JSDM using six datasets that vary widely in numbers of sites, species, and environmental covariates considered. Our singular notation shows that many of the JSDMs are very similar, and in turn parameter estimates of different JSDMs are moderate to strongly, positively correlated. In contrast, the different JSDMs clearly differ in computational efficiency and memory limitations. Our framework will allow ecologists to make educated decisions about the JSDM that best suits their objective, and enable wider uptake of JSDM methods among the ecological community.

AB - Joint species distribution models (JSDMs) account for biotic interactions and missing environmental predictors in correlative species distribution models. Several different JSDMs have been proposed in the literature, but the use of different or conflicting nomenclature and statistical notation potentially obscures similarities and differences among them. Furthermore, new JSDM implementations have been illustrated with different case studies, preventing direct comparisons of computational and statistical performance. We aim to resolve these outstanding issues by (a) highlighting similarities among seven presence–absence JSDMs using a clearly defined, singular notation; and (b) evaluating the computational and statistical performance of each JSDM using six datasets that vary widely in numbers of sites, species, and environmental covariates considered. Our singular notation shows that many of the JSDMs are very similar, and in turn parameter estimates of different JSDMs are moderate to strongly, positively correlated. In contrast, the different JSDMs clearly differ in computational efficiency and memory limitations. Our framework will allow ecologists to make educated decisions about the JSDM that best suits their objective, and enable wider uptake of JSDM methods among the ecological community.

KW - biotic interactions

KW - community assembly

KW - hierarchical models

KW - joint species distribution model

KW - latent factors

KW - presence–absence

KW - residual correlation

UR - http://www.scopus.com/inward/record.url?scp=85055951003&partnerID=8YFLogxK

U2 - 10.1111/2041-210X.13106

DO - 10.1111/2041-210X.13106

M3 - Article

VL - 10

SP - 198

EP - 211

JO - Methods in Ecology and Evolution

JF - Methods in Ecology and Evolution

SN - 2041-210X

IS - 2

ER -