Randomization of presence-absence matrices

Comments and new algorithms

Research output: Contribution to journalArticle

161 Citations (Scopus)

Abstract

Randomization of presence-absence data matrices with fixed row and column totals is an important tool in ecological research wherever the significance of data-based statistics (e.g., species association measures) is to be evaluated. In the current literature of numerical ecology, however, there has been no algorithm that randomizes moderately large matrices in short time such that equidistribution of results is guaranteed. We show that a simple modification of the swap algorithm, called here the "trial-swap method," satisfies the requirement for equidistribution. Since this is relatively slow, we suggest two fast algorithms that, combined with the trial-swap method, produce all possible results with equal chance. The three procedures are illustrated using actual examples taken from bird biogeography and vegetation ecology.

Original languageEnglish
Pages (from-to)86-92
Number of pages7
JournalEcology
Volume85
Issue number1
Publication statusPublished - Jan 2004

Fingerprint

matrix
ecology
biogeography
statistics
bird
vegetation
birds
methodology
method
trial

Keywords

  • Data matrices
  • Null models
  • Presence-absence data
  • Randomization methods
  • Species association
  • Swap methods
  • Vanuatu data

ASJC Scopus subject areas

  • Ecology

Cite this

Randomization of presence-absence matrices : Comments and new algorithms. / Miklós, I.; Podaní, J.

In: Ecology, Vol. 85, No. 1, 01.2004, p. 86-92.

Research output: Contribution to journalArticle

@article{bef015d5027442e09d61b1c86cc39bb2,
title = "Randomization of presence-absence matrices: Comments and new algorithms",
abstract = "Randomization of presence-absence data matrices with fixed row and column totals is an important tool in ecological research wherever the significance of data-based statistics (e.g., species association measures) is to be evaluated. In the current literature of numerical ecology, however, there has been no algorithm that randomizes moderately large matrices in short time such that equidistribution of results is guaranteed. We show that a simple modification of the swap algorithm, called here the {"}trial-swap method,{"} satisfies the requirement for equidistribution. Since this is relatively slow, we suggest two fast algorithms that, combined with the trial-swap method, produce all possible results with equal chance. The three procedures are illustrated using actual examples taken from bird biogeography and vegetation ecology.",
keywords = "Data matrices, Null models, Presence-absence data, Randomization methods, Species association, Swap methods, Vanuatu data",
author = "I. Mikl{\'o}s and J. Podan{\'i}",
year = "2004",
month = "1",
language = "English",
volume = "85",
pages = "86--92",
journal = "Ecology",
issn = "0012-9658",
publisher = "Ecological Society of America",
number = "1",

}

TY - JOUR

T1 - Randomization of presence-absence matrices

T2 - Comments and new algorithms

AU - Miklós, I.

AU - Podaní, J.

PY - 2004/1

Y1 - 2004/1

N2 - Randomization of presence-absence data matrices with fixed row and column totals is an important tool in ecological research wherever the significance of data-based statistics (e.g., species association measures) is to be evaluated. In the current literature of numerical ecology, however, there has been no algorithm that randomizes moderately large matrices in short time such that equidistribution of results is guaranteed. We show that a simple modification of the swap algorithm, called here the "trial-swap method," satisfies the requirement for equidistribution. Since this is relatively slow, we suggest two fast algorithms that, combined with the trial-swap method, produce all possible results with equal chance. The three procedures are illustrated using actual examples taken from bird biogeography and vegetation ecology.

AB - Randomization of presence-absence data matrices with fixed row and column totals is an important tool in ecological research wherever the significance of data-based statistics (e.g., species association measures) is to be evaluated. In the current literature of numerical ecology, however, there has been no algorithm that randomizes moderately large matrices in short time such that equidistribution of results is guaranteed. We show that a simple modification of the swap algorithm, called here the "trial-swap method," satisfies the requirement for equidistribution. Since this is relatively slow, we suggest two fast algorithms that, combined with the trial-swap method, produce all possible results with equal chance. The three procedures are illustrated using actual examples taken from bird biogeography and vegetation ecology.

KW - Data matrices

KW - Null models

KW - Presence-absence data

KW - Randomization methods

KW - Species association

KW - Swap methods

KW - Vanuatu data

UR - http://www.scopus.com/inward/record.url?scp=1342268887&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1342268887&partnerID=8YFLogxK

M3 - Article

VL - 85

SP - 86

EP - 92

JO - Ecology

JF - Ecology

SN - 0012-9658

IS - 1

ER -