This is a test version of Biostars. For the public version, visit https://www.biostars.org.
Concerning FDR calculation using Limma

I'm new to microarray and I'm trying to analyze several single channel agilent microarray using Limma package.
I have a question concerning the calculation of FDR q value using eBayes/topTable.
If I understood well, q value is an adjustment of p value linked to gene ranking. So, should the q value be calculated on an entire dataset or should it be calculated after filtering (removing non-coding RNA for instance)? As the number of variables will be different, the ranking should also be, will this impact the q value?

Thanks!

agilent microarray limma fdr
• 3,831 views • link
written by sebastien200109 • sebastien200109

If your problem got solved, please accept the answer by clicking on the green tick, which only you could see below the answer.

• 0 views • link
updated by Ram Ram • written by Deepak Tanwar Deepak Tanwar

1 answer

You typically want to calculate q-values and adjusted p-values (they're different, though related) from your filtered dataset (assuming you're filtering by things like coding status or other factors independent from the p-value).

• 0 views • link
written by Devon Ryan Devon Ryan

Log in to answer this question.

More posts like this