Thanks Jim, you are absolutely right. Pasting the code would have clearly shown that I did something wrong. Meanwhile I figured out myself, that the F p-value gets only corrected with an additional parameter like here: write.fit(fit2, file="file", sep="\t", adjust='fdr', F.adjust='fdr') Pascal On 03/29/2012 03:51 PM, James W. MacDonald wrote: > Hi Pascal, > > On 3/29/2012 9:20 AM, Pascal Gellert wrote: >> Dear Bioconductor members, >> >> I am using limma to analyze my microarrays. Therefore I apply lmFit >> and eBayes on my normalized data. Finally I write the result to a >> text file by write.fit function. For multiple testing correction I >> chose adjust='fdr' in the write.fit function. Usually everything >> works just as it should. However in some cases, the result file does >> not contain the column "F p.value.adj". The columns with the adjusted >> p-values ("p.value.adj") and p-value for the F-statistic ("F >> p.value") are present. >> Obviously I am doing something wrong, but I cannot figure out what it >> is since I am using exactly the same code for different data sets and >> the "F p.value.adj" column does not show up for one data set only. >> >> Thanks for your help, >> >> Pascal >> >> >> R version 2.10.1 (2009-12-14) >> limma_3.2.3 > > You need to do two things first. One, update to a current version of > R. Two, give a small, reproducible code example. > > Best, > > Jim > > >> >> _______________________________________________ >> 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 >