Mercurial > repos > lecorguille > anova
changeset 11:102049093b7d draft default tip
planemo upload for repository https://github.com/workflow4metabolomics/anova commit 4922313a0e9569326b7723c41babb89f998dbfd9
| author | lecorguille |
|---|---|
| date | Tue, 13 Mar 2018 09:47:21 -0400 |
| parents | b147b17759a6 |
| children | |
| files | abims_anova.r abims_anova.xml |
| diffstat | 2 files changed, 8 insertions(+), 3 deletions(-) [+] |
line wrap: on
line diff
--- a/abims_anova.r Wed Feb 28 07:44:13 2018 -0500 +++ b/abims_anova.r Tue Mar 13 09:47:21 2018 -0400 @@ -24,7 +24,7 @@ # -- import -- data=read.table(file, header = TRUE, row.names=1, sep = sep, quote="\"", dec = dec, fill = TRUE, comment.char="",na.strings = "NA", check.names=FALSE) - if (mode == "row") data=t(data) + if (mode == "row") {data=t(data)} else {data=as.matrix(data)} sampleinfoTab=read.table(sampleinfo, header = TRUE, row.names=1, sep = sep, quote="\"") rownames(sampleinfoTab) = make.names(rownames(sampleinfoTab))
--- a/abims_anova.xml Wed Feb 28 07:44:13 2018 -0500 +++ b/abims_anova.xml Tue Mar 13 09:47:21 2018 -0400 @@ -1,4 +1,4 @@ -<tool id="abims_anova" name="Anova" version="1.2.0"> +<tool id="abims_anova" name="Anova" version="1.2.1"> <description>N-way anova. With ou Without interactions</description> @@ -29,7 +29,7 @@ </command> <inputs> - <param name="input" type="data" label="Data Matrix file" format="tabular" help="Matrix of numeric data with headers." /> + <param name="input" type="data" label="Data Matrix file" format="tabular,csv" help="Matrix of numeric data with headers." /> <param name="sampleinfo" type="data" label="Sample Metadata file" format="tabular" help="Tabular file with the data metadata : one sample per line and at least two columns : ids and one condition" /> <param name="varinfo" type="data" label="Variable Metadata file" format="tabular" help="Tabular file with information about your tested variables. Only used to aggregate generated information." /> @@ -121,6 +121,11 @@ Analysis of variance (ANOVA) is used to analyze the differences between group means and their associated procedures, in which the observed variance in a particular variable is partitioned into components attributable to different sources of variation. +**Note about sum of squares (SS) calculation of N-way ANOVA in this module.** +This module use R function *manova()* (and thus R function *aov()*) to establish N-way ANOVA. +Therefore calculated sum of squares are sequential ones (sometimes called "Type I SS"). +If your design is unbalanced, this may not correspond to the type of hypothesis being of interest. +Note that you can obtain adjusted sums of squares ("Type II SS") by running several times this module with different orders in factors. -----------