Hi, I need help for using one way anova for microarray data. In 20 files, I have 5 treatment and 4 replicates for each treatment. I have the following code: . . . treatment <- gl(5,4,20, label=c("T1","T2","T3","T4","T5")) # define ANOVA function aof <- function(x) { m<-data.frame(treatment, x); anova(aov(x ~ treatment, m)) } anovaresults <- apply(sdata, 1, aof) Can you suggest how can I do one way ANOVA for 5 treatment and to make all the comparations between treatments? [[alternative HTML version deleted]]

You don't want to do things that way. Instead, you want to use either limma, multtest, sigggenes, etc. Personally I tend towards limma. library(BiocInstaller) biocLite(limma) library(limma) limmaUsersGuide() will get you started. Best, Jim On 12/13/2012 10:39 AM, listas de consultas wrote: > Hi, > > I need help for using one way anova for microarray data. > In 20 files, I have 5 treatment and 4 replicates for each treatment. > > I have the following code: > > . > . > . > treatment<- gl(5,4,20, label=c("T1","T2","T3","T4","T5")) > # define ANOVA function > aof<- function(x) { > m<-data.frame(treatment, x); > anova(aov(x ~ treatment, m)) > } > > anovaresults<- apply(sdata, 1, aof) > > > Can you suggest how can I do one way ANOVA for 5 treatment and to make > all the comparations between treatments? > > [[alternative HTML version deleted]] > > _______________________________________________ > Bioconductor mailing list > Bioconductor at r-project.org > https://stat.ethz.ch/mailman/listinfo/bioconductor > Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor -- James W. MacDonald, M.S. Biostatistician University of Washington Environmental and Occupational Health Sciences 4225 Roosevelt Way NE, # 100 Seattle WA 98105-6099