[BioC] limma and Rank Products: comparison of the number of results

[Juan Carlos Oliveros]

Wolfgang,

We apply this kind of methods just to find candidates to be confirmed 
experimentally in posterior analysis. We expect to have a percentage of 
false positives which is better for us than having false negatives.

But with independence of the cutoff, we observed that --in this case-- 
Rank Products provides less statistically significant results than limma 
which was not the case in the past. I just want to know if people that 
use both methods obtain the same differences.

Thanks a lot.

Juan Carlos

Wolfgang Huber wrote:
> Juan
>
> did you verify whether your estimates of "FDR" or "Percentage of false prediction", in the way you apply them, are actually accurate, e.g. by independent validation experiments, or by applying your method to biological replicates (where you know that all discoveries are in fact false)?
>
>            Best wishes
>                   Wolfgang
>
>
> Il giorno Feb 17, 2010, alle ore 3:10 PM, Juan Carlos Oliveros ha scritto:
>
> Dear all
>
> When working with comparative experiment based on Affymetrix gene expression arrays I usually apply one of the following combination of methods:
>
> RMA + limma + FDR
>
> or
>
> RMA+ Rank Products
> (rank products "Percentage of false prediction" values are supposed to be equivalent to FDR)
>
> Usually we obtain much more differentially expressed genes when using Rank Products than when using limma at the same FDR threshold.
>
> I wonder if in your case is the same. Do you obtain many more results with Rank Products than with limma at the same FDR cutoff?
>
> In a recent experiment we obtained the opposite (more results with limma) and I'd like to know your experience when using both methods regarding the number of results.
>
> best,
>
> Juan Carlos Oliveros, Ph.D.
> CNB-CSIC, Madrid, Spain
>
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/bioconductor
> Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor
>
> Wolfgang Huber
> whuber at embl.de
>
>
>
>