Simultaneous confidence intervals for comparing biodiversity indices estimated from overdispersed count data

Research output: Contribution to journalArticleResearchpeer review

Authors

Research Organisations

External Research Organisations

  • Hannover Medical School (MHH)
  • Julius Kühn Institute - Federal Research Centre for Cultivated Plants (JKI)
  • Bavarian State Research Center for Agriculture (LfL)
View graph of relations

Details

Original languageEnglish
Pages (from-to)246-263
Number of pages18
JournalBiometrical Journal
Volume55
Issue number2
Early online date11 Feb 2013
Publication statusPublished - Mar 2013

Abstract

Diversity indices might be used to assess the impact of treatments on the relative abundance patterns in species communities. When several treatments are to be compared, simultaneous confidence intervals for the differences of diversity indices between treatments may be used. The simultaneous confidence interval methods described until now are either constructed or validated under the assumption of the multinomial distribution for the abundance counts. Motivated by four example data sets with background in agricultural and marine ecology, we focus on the situation when available replications show that the count data exhibit extra-multinomial variability. Based on simulated overdispersed count data, we compare previously proposed methods assuming multinomial distribution, a method assuming normal distribution for the replicated observations of the diversity indices and three different bootstrap methods to construct simultaneous confidence intervals for multiple differences of Simpson and Shannon diversity indices. The focus of the simulation study is on comparisons to a control group. The severe failure of asymptotic multinomial methods in overdispersed settings is illustrated. Among the bootstrap methods, the widely known Westfall-Young method performs best for the Simpson index, while for the Shannon index, two methods based on stratified bootstrap and summed count data are preferable. The methods application is illustrated for an example.

Keywords

    Bootstrap, Extra-multinomial variability, Overdispersion, Shannon index, Simpson index, Simultaneous coverage probability

ASJC Scopus subject areas

Sustainable Development Goals

Cite this

Simultaneous confidence intervals for comparing biodiversity indices estimated from overdispersed count data. / Scherer, Ralph; Schaarschmidt, Frank; Prescher, Sabine et al.
In: Biometrical Journal, Vol. 55, No. 2, 03.2013, p. 246-263.

Research output: Contribution to journalArticleResearchpeer review

Scherer R, Schaarschmidt F, Prescher S, Priesnitz KU. Simultaneous confidence intervals for comparing biodiversity indices estimated from overdispersed count data. Biometrical Journal. 2013 Mar;55(2):246-263. Epub 2013 Feb 11. doi: 10.1002/bimj.201200157
Download
@article{4cb0b5a118f743749624c9a100faa90c,
title = "Simultaneous confidence intervals for comparing biodiversity indices estimated from overdispersed count data",
abstract = "Diversity indices might be used to assess the impact of treatments on the relative abundance patterns in species communities. When several treatments are to be compared, simultaneous confidence intervals for the differences of diversity indices between treatments may be used. The simultaneous confidence interval methods described until now are either constructed or validated under the assumption of the multinomial distribution for the abundance counts. Motivated by four example data sets with background in agricultural and marine ecology, we focus on the situation when available replications show that the count data exhibit extra-multinomial variability. Based on simulated overdispersed count data, we compare previously proposed methods assuming multinomial distribution, a method assuming normal distribution for the replicated observations of the diversity indices and three different bootstrap methods to construct simultaneous confidence intervals for multiple differences of Simpson and Shannon diversity indices. The focus of the simulation study is on comparisons to a control group. The severe failure of asymptotic multinomial methods in overdispersed settings is illustrated. Among the bootstrap methods, the widely known Westfall-Young method performs best for the Simpson index, while for the Shannon index, two methods based on stratified bootstrap and summed count data are preferable. The methods application is illustrated for an example.",
keywords = "Bootstrap, Extra-multinomial variability, Overdispersion, Shannon index, Simpson index, Simultaneous coverage probability",
author = "Ralph Scherer and Frank Schaarschmidt and Sabine Prescher and Priesnitz, {Kai U.}",
year = "2013",
month = mar,
doi = "10.1002/bimj.201200157",
language = "English",
volume = "55",
pages = "246--263",
journal = "Biometrical Journal",
issn = "0323-3847",
publisher = "Wiley-VCH Verlag",
number = "2",

}

Download

TY - JOUR

T1 - Simultaneous confidence intervals for comparing biodiversity indices estimated from overdispersed count data

AU - Scherer, Ralph

AU - Schaarschmidt, Frank

AU - Prescher, Sabine

AU - Priesnitz, Kai U.

PY - 2013/3

Y1 - 2013/3

N2 - Diversity indices might be used to assess the impact of treatments on the relative abundance patterns in species communities. When several treatments are to be compared, simultaneous confidence intervals for the differences of diversity indices between treatments may be used. The simultaneous confidence interval methods described until now are either constructed or validated under the assumption of the multinomial distribution for the abundance counts. Motivated by four example data sets with background in agricultural and marine ecology, we focus on the situation when available replications show that the count data exhibit extra-multinomial variability. Based on simulated overdispersed count data, we compare previously proposed methods assuming multinomial distribution, a method assuming normal distribution for the replicated observations of the diversity indices and three different bootstrap methods to construct simultaneous confidence intervals for multiple differences of Simpson and Shannon diversity indices. The focus of the simulation study is on comparisons to a control group. The severe failure of asymptotic multinomial methods in overdispersed settings is illustrated. Among the bootstrap methods, the widely known Westfall-Young method performs best for the Simpson index, while for the Shannon index, two methods based on stratified bootstrap and summed count data are preferable. The methods application is illustrated for an example.

AB - Diversity indices might be used to assess the impact of treatments on the relative abundance patterns in species communities. When several treatments are to be compared, simultaneous confidence intervals for the differences of diversity indices between treatments may be used. The simultaneous confidence interval methods described until now are either constructed or validated under the assumption of the multinomial distribution for the abundance counts. Motivated by four example data sets with background in agricultural and marine ecology, we focus on the situation when available replications show that the count data exhibit extra-multinomial variability. Based on simulated overdispersed count data, we compare previously proposed methods assuming multinomial distribution, a method assuming normal distribution for the replicated observations of the diversity indices and three different bootstrap methods to construct simultaneous confidence intervals for multiple differences of Simpson and Shannon diversity indices. The focus of the simulation study is on comparisons to a control group. The severe failure of asymptotic multinomial methods in overdispersed settings is illustrated. Among the bootstrap methods, the widely known Westfall-Young method performs best for the Simpson index, while for the Shannon index, two methods based on stratified bootstrap and summed count data are preferable. The methods application is illustrated for an example.

KW - Bootstrap

KW - Extra-multinomial variability

KW - Overdispersion

KW - Shannon index

KW - Simpson index

KW - Simultaneous coverage probability

UR - http://www.scopus.com/inward/record.url?scp=84874996461&partnerID=8YFLogxK

U2 - 10.1002/bimj.201200157

DO - 10.1002/bimj.201200157

M3 - Article

C2 - 23401312

AN - SCOPUS:84874996461

VL - 55

SP - 246

EP - 263

JO - Biometrical Journal

JF - Biometrical Journal

SN - 0323-3847

IS - 2

ER -

By the same author(s)