Dismantling the Mantel tests

Publication: Research - peer-reviewJournal article – Annual report year: 2013

Standard

Dismantling the Mantel tests. / Guillot, Gilles; Rousset, François.

In: Methods in Ecology and Evolution, Vol. 4, No. 4, 2013, p. 336–344.

Publication: Research - peer-reviewJournal article – Annual report year: 2013

Harvard

APA

CBE

MLA

Vancouver

Author

Guillot, Gilles; Rousset, François / Dismantling the Mantel tests.

In: Methods in Ecology and Evolution, Vol. 4, No. 4, 2013, p. 336–344.

Publication: Research - peer-reviewJournal article – Annual report year: 2013

Bibtex

@article{f205888301084412a6ec68c712ae7018,
title = "Dismantling the Mantel tests",
keywords = "Landscape ecology, Landscape genetics, Phylogeography, Geographic epidemiology, Spatial structure, Isolation by distance, Isolation by resistance, Autocorrelation, Type I error, Loa loa",
publisher = "Wiley-Blackwell Publishing Ltd.",
author = "Gilles Guillot and François Rousset",
year = "2013",
doi = "10.1111/2041-210x.12018",
volume = "4",
number = "4",
pages = "336–344",
journal = "Methods in Ecology and Evolution",
issn = "2041-210X",

}

RIS

TY - JOUR

T1 - Dismantling the Mantel tests

A1 - Guillot,Gilles

A1 - Rousset,François

AU - Guillot,Gilles

AU - Rousset,François

PB - Wiley-Blackwell Publishing Ltd.

PY - 2013

Y1 - 2013

N2 - 1. The simple and partialMantel tests are routinely used in many areas of evolutionary biology to assess the significance of the association between two ormorematrices of distances relative to the same pairs of individuals or demes. Partial Mantel tests rather than simple Mantel tests are widely used to assess the relationship between two variables displaying some form of structure.<br/><br/>2. We show that contrary to a widely shared belief, partialMantel tests are not valid in this case, and their bias remains close to that of the simpleMantel test.<br/><br/>3. We confirm that strong biases are expected under a sampling design and spatial correlation parameter drawn from an actual study.<br/><br/>4. TheMantel tests should not be used in case autocorrelation is suspected in both variables compared under the null hypothesis.We outline alternative strategies. The R code used for our computer simulations is distributed as supportingmaterial.

AB - 1. The simple and partialMantel tests are routinely used in many areas of evolutionary biology to assess the significance of the association between two ormorematrices of distances relative to the same pairs of individuals or demes. Partial Mantel tests rather than simple Mantel tests are widely used to assess the relationship between two variables displaying some form of structure.<br/><br/>2. We show that contrary to a widely shared belief, partialMantel tests are not valid in this case, and their bias remains close to that of the simpleMantel test.<br/><br/>3. We confirm that strong biases are expected under a sampling design and spatial correlation parameter drawn from an actual study.<br/><br/>4. TheMantel tests should not be used in case autocorrelation is suspected in both variables compared under the null hypothesis.We outline alternative strategies. The R code used for our computer simulations is distributed as supportingmaterial.

KW - Landscape ecology

KW - Landscape genetics

KW - Phylogeography

KW - Geographic epidemiology

KW - Spatial structure

KW - Isolation by distance

KW - Isolation by resistance

KW - Autocorrelation

KW - Type I error

KW - Loa loa

U2 - 10.1111/2041-210x.12018

DO - 10.1111/2041-210x.12018

JO - Methods in Ecology and Evolution

JF - Methods in Ecology and Evolution

SN - 2041-210X

IS - 4

VL - 4

SP - 336

EP - 344

ER -