Reassess the t test: Interact with all your data via ANOVA

Siobhan M. Brady, Meike Burow, Wolfgang Busch, Õrjan Carlborg, Katherine J. Denby, Jane Glazebrook, Eric S. Hamilton, Stacey L. Harmer, Elizabeth S. Haswell, Julin N. Maloof, Nathan M Springer, Daniel J. Kliebenstein

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Plant biology is rapidly entering an era where we have the ability to conduct intricate studies that investigate how a plant interacts with the entirety of its environment. This requires complex, large studies to measure how plant genotypes simultaneously interact with a diverse array of environmental stimuli. Successful interpretation of the results from these studies requires us to transition away from the traditional standard of conducting an array of pairwise t tests toward more general linear modeling structures, such as those provided by the extendable ANOVA framework. In this Perspective, we present arguments for making this transition and illustrate how it will help to avoid incorrect conclusions in factorial interaction studies (genotype x genotype, genotype x treatment, and treatment x treatment, or higher levels of interaction) that are becoming more prevalent in this new era of plant biology.

Original languageEnglish (US)
Pages (from-to)2088-2094
Number of pages7
JournalPlant Cell
Volume27
Issue number8
DOIs
StatePublished - Aug 1 2015

Fingerprint

Analysis of Variance
analysis of variance
Genotype
genotype
plant biology
t-test

Cite this

Brady, S. M., Burow, M., Busch, W., Carlborg, Õ., Denby, K. J., Glazebrook, J., ... Kliebenstein, D. J. (2015). Reassess the t test: Interact with all your data via ANOVA. Plant Cell, 27(8), 2088-2094. https://doi.org/10.1105/tpc.15.00238

Reassess the t test : Interact with all your data via ANOVA. / Brady, Siobhan M.; Burow, Meike; Busch, Wolfgang; Carlborg, Õrjan; Denby, Katherine J.; Glazebrook, Jane; Hamilton, Eric S.; Harmer, Stacey L.; Haswell, Elizabeth S.; Maloof, Julin N.; Springer, Nathan M; Kliebenstein, Daniel J.

In: Plant Cell, Vol. 27, No. 8, 01.08.2015, p. 2088-2094.

Research output: Contribution to journalArticle

Brady, SM, Burow, M, Busch, W, Carlborg, Õ, Denby, KJ, Glazebrook, J, Hamilton, ES, Harmer, SL, Haswell, ES, Maloof, JN, Springer, NM & Kliebenstein, DJ 2015, 'Reassess the t test: Interact with all your data via ANOVA', Plant Cell, vol. 27, no. 8, pp. 2088-2094. https://doi.org/10.1105/tpc.15.00238
Brady SM, Burow M, Busch W, Carlborg Õ, Denby KJ, Glazebrook J et al. Reassess the t test: Interact with all your data via ANOVA. Plant Cell. 2015 Aug 1;27(8):2088-2094. https://doi.org/10.1105/tpc.15.00238
Brady, Siobhan M. ; Burow, Meike ; Busch, Wolfgang ; Carlborg, Õrjan ; Denby, Katherine J. ; Glazebrook, Jane ; Hamilton, Eric S. ; Harmer, Stacey L. ; Haswell, Elizabeth S. ; Maloof, Julin N. ; Springer, Nathan M ; Kliebenstein, Daniel J. / Reassess the t test : Interact with all your data via ANOVA. In: Plant Cell. 2015 ; Vol. 27, No. 8. pp. 2088-2094.
@article{de5317c793274f219f6ec88244a9c747,
title = "Reassess the t test: Interact with all your data via ANOVA",
abstract = "Plant biology is rapidly entering an era where we have the ability to conduct intricate studies that investigate how a plant interacts with the entirety of its environment. This requires complex, large studies to measure how plant genotypes simultaneously interact with a diverse array of environmental stimuli. Successful interpretation of the results from these studies requires us to transition away from the traditional standard of conducting an array of pairwise t tests toward more general linear modeling structures, such as those provided by the extendable ANOVA framework. In this Perspective, we present arguments for making this transition and illustrate how it will help to avoid incorrect conclusions in factorial interaction studies (genotype x genotype, genotype x treatment, and treatment x treatment, or higher levels of interaction) that are becoming more prevalent in this new era of plant biology.",
author = "Brady, {Siobhan M.} and Meike Burow and Wolfgang Busch and {\~O}rjan Carlborg and Denby, {Katherine J.} and Jane Glazebrook and Hamilton, {Eric S.} and Harmer, {Stacey L.} and Haswell, {Elizabeth S.} and Maloof, {Julin N.} and Springer, {Nathan M} and Kliebenstein, {Daniel J.}",
year = "2015",
month = "8",
day = "1",
doi = "10.1105/tpc.15.00238",
language = "English (US)",
volume = "27",
pages = "2088--2094",
journal = "Plant Cell",
issn = "1040-4651",
publisher = "American Society of Plant Biologists",
number = "8",

}

TY - JOUR

T1 - Reassess the t test

T2 - Interact with all your data via ANOVA

AU - Brady, Siobhan M.

AU - Burow, Meike

AU - Busch, Wolfgang

AU - Carlborg, Õrjan

AU - Denby, Katherine J.

AU - Glazebrook, Jane

AU - Hamilton, Eric S.

AU - Harmer, Stacey L.

AU - Haswell, Elizabeth S.

AU - Maloof, Julin N.

AU - Springer, Nathan M

AU - Kliebenstein, Daniel J.

PY - 2015/8/1

Y1 - 2015/8/1

N2 - Plant biology is rapidly entering an era where we have the ability to conduct intricate studies that investigate how a plant interacts with the entirety of its environment. This requires complex, large studies to measure how plant genotypes simultaneously interact with a diverse array of environmental stimuli. Successful interpretation of the results from these studies requires us to transition away from the traditional standard of conducting an array of pairwise t tests toward more general linear modeling structures, such as those provided by the extendable ANOVA framework. In this Perspective, we present arguments for making this transition and illustrate how it will help to avoid incorrect conclusions in factorial interaction studies (genotype x genotype, genotype x treatment, and treatment x treatment, or higher levels of interaction) that are becoming more prevalent in this new era of plant biology.

AB - Plant biology is rapidly entering an era where we have the ability to conduct intricate studies that investigate how a plant interacts with the entirety of its environment. This requires complex, large studies to measure how plant genotypes simultaneously interact with a diverse array of environmental stimuli. Successful interpretation of the results from these studies requires us to transition away from the traditional standard of conducting an array of pairwise t tests toward more general linear modeling structures, such as those provided by the extendable ANOVA framework. In this Perspective, we present arguments for making this transition and illustrate how it will help to avoid incorrect conclusions in factorial interaction studies (genotype x genotype, genotype x treatment, and treatment x treatment, or higher levels of interaction) that are becoming more prevalent in this new era of plant biology.

UR - http://www.scopus.com/inward/record.url?scp=84941313296&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941313296&partnerID=8YFLogxK

U2 - 10.1105/tpc.15.00238

DO - 10.1105/tpc.15.00238

M3 - Article

C2 - 26220933

AN - SCOPUS:84941313296

VL - 27

SP - 2088

EP - 2094

JO - Plant Cell

JF - Plant Cell

SN - 1040-4651

IS - 8

ER -