On tests of spatial pattern based on simulation envelopes

Adrian Baddeley, Peter J. Diggle, Andrew Hardegen, Thomas Lawrence, Robin K. Milne, Gopalan Nair

Research output: Contribution to journalArticle

Abstract

In the analysis of spatial point patterns, an important role is played by statistical tests based on simulation envelopes, such as the envelope of simulations of Ripley's K function. Recent ecological literature has correctly pointed out a common error in the interpretation of simulation envelopes. However, this has led to a widespread belief that the tests themselves are invalid. On the contrary, envelope-based statistical tests are correct statistical procedures, under appropriate conditions. In this paper, we explain the principles of Monte Carlo tests and their correct interpretation, canvas the benefits of graphical procedures, measure the statistical performance of several popular tests, and make practical recommendations. There are several caveats including the under-recognized problem that Monte Carlo tests of goodness of fit are probably conservative if the model parameters have to be estimated from data. Finally, we discuss whether graphs of simulation envelopes can be used to infer the scale of spatial interaction.

Original languageEnglish (US)
Pages (from-to)477-489
Number of pages13
JournalEcological Monographs
Volume84
Issue number3
DOIs
StatePublished - 2014
Externally publishedYes

Fingerprint

simulation
statistical analysis
testing
test
parameter
analysis
recommendation

Keywords

  • Confidence bands
  • Conservative test
  • Deviation test
  • Global test
  • K function
  • Monte Carlo test
  • Null model
  • Pair correlation function
  • Pointwise test
  • Scale of interaction
  • Spatial point pattern
  • Variance stabilization

ASJC Scopus subject areas

  • Ecology, Evolution, Behavior and Systematics

Cite this

Baddeley, A., Diggle, P. J., Hardegen, A., Lawrence, T., Milne, R. K., & Nair, G. (2014). On tests of spatial pattern based on simulation envelopes. Ecological Monographs, 84(3), 477-489. https://doi.org/10.1890/13-2042.1

On tests of spatial pattern based on simulation envelopes. / Baddeley, Adrian; Diggle, Peter J.; Hardegen, Andrew; Lawrence, Thomas; Milne, Robin K.; Nair, Gopalan.

In: Ecological Monographs, Vol. 84, No. 3, 2014, p. 477-489.

Research output: Contribution to journalArticle

Baddeley, A, Diggle, PJ, Hardegen, A, Lawrence, T, Milne, RK & Nair, G 2014, 'On tests of spatial pattern based on simulation envelopes', Ecological Monographs, vol. 84, no. 3, pp. 477-489. https://doi.org/10.1890/13-2042.1
Baddeley A, Diggle PJ, Hardegen A, Lawrence T, Milne RK, Nair G. On tests of spatial pattern based on simulation envelopes. Ecological Monographs. 2014;84(3):477-489. https://doi.org/10.1890/13-2042.1
Baddeley, Adrian ; Diggle, Peter J. ; Hardegen, Andrew ; Lawrence, Thomas ; Milne, Robin K. ; Nair, Gopalan. / On tests of spatial pattern based on simulation envelopes. In: Ecological Monographs. 2014 ; Vol. 84, No. 3. pp. 477-489.
@article{8d93fd730e444786862e929c7d1996ef,
title = "On tests of spatial pattern based on simulation envelopes",
abstract = "In the analysis of spatial point patterns, an important role is played by statistical tests based on simulation envelopes, such as the envelope of simulations of Ripley's K function. Recent ecological literature has correctly pointed out a common error in the interpretation of simulation envelopes. However, this has led to a widespread belief that the tests themselves are invalid. On the contrary, envelope-based statistical tests are correct statistical procedures, under appropriate conditions. In this paper, we explain the principles of Monte Carlo tests and their correct interpretation, canvas the benefits of graphical procedures, measure the statistical performance of several popular tests, and make practical recommendations. There are several caveats including the under-recognized problem that Monte Carlo tests of goodness of fit are probably conservative if the model parameters have to be estimated from data. Finally, we discuss whether graphs of simulation envelopes can be used to infer the scale of spatial interaction.",
keywords = "Confidence bands, Conservative test, Deviation test, Global test, K function, Monte Carlo test, Null model, Pair correlation function, Pointwise test, Scale of interaction, Spatial point pattern, Variance stabilization",
author = "Adrian Baddeley and Diggle, {Peter J.} and Andrew Hardegen and Thomas Lawrence and Milne, {Robin K.} and Gopalan Nair",
year = "2014",
doi = "10.1890/13-2042.1",
language = "English (US)",
volume = "84",
pages = "477--489",
journal = "Ecological Monographs",
issn = "0012-9615",
publisher = "Ecological Society of America",
number = "3",

}

TY - JOUR

T1 - On tests of spatial pattern based on simulation envelopes

AU - Baddeley, Adrian

AU - Diggle, Peter J.

AU - Hardegen, Andrew

AU - Lawrence, Thomas

AU - Milne, Robin K.

AU - Nair, Gopalan

PY - 2014

Y1 - 2014

N2 - In the analysis of spatial point patterns, an important role is played by statistical tests based on simulation envelopes, such as the envelope of simulations of Ripley's K function. Recent ecological literature has correctly pointed out a common error in the interpretation of simulation envelopes. However, this has led to a widespread belief that the tests themselves are invalid. On the contrary, envelope-based statistical tests are correct statistical procedures, under appropriate conditions. In this paper, we explain the principles of Monte Carlo tests and their correct interpretation, canvas the benefits of graphical procedures, measure the statistical performance of several popular tests, and make practical recommendations. There are several caveats including the under-recognized problem that Monte Carlo tests of goodness of fit are probably conservative if the model parameters have to be estimated from data. Finally, we discuss whether graphs of simulation envelopes can be used to infer the scale of spatial interaction.

AB - In the analysis of spatial point patterns, an important role is played by statistical tests based on simulation envelopes, such as the envelope of simulations of Ripley's K function. Recent ecological literature has correctly pointed out a common error in the interpretation of simulation envelopes. However, this has led to a widespread belief that the tests themselves are invalid. On the contrary, envelope-based statistical tests are correct statistical procedures, under appropriate conditions. In this paper, we explain the principles of Monte Carlo tests and their correct interpretation, canvas the benefits of graphical procedures, measure the statistical performance of several popular tests, and make practical recommendations. There are several caveats including the under-recognized problem that Monte Carlo tests of goodness of fit are probably conservative if the model parameters have to be estimated from data. Finally, we discuss whether graphs of simulation envelopes can be used to infer the scale of spatial interaction.

KW - Confidence bands

KW - Conservative test

KW - Deviation test

KW - Global test

KW - K function

KW - Monte Carlo test

KW - Null model

KW - Pair correlation function

KW - Pointwise test

KW - Scale of interaction

KW - Spatial point pattern

KW - Variance stabilization

UR - http://www.scopus.com/inward/record.url?scp=84905640072&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905640072&partnerID=8YFLogxK

U2 - 10.1890/13-2042.1

DO - 10.1890/13-2042.1

M3 - Article

AN - SCOPUS:84905640072

VL - 84

SP - 477

EP - 489

JO - Ecological Monographs

JF - Ecological Monographs

SN - 0012-9615

IS - 3

ER -