[BioC] edgeR - p.adjust

Steve Lianoglou mailinglist.honeypot at gmail.com
Wed Feb 23 22:31:29 CET 2011


Hi,

On Wed, Feb 23, 2011 at 4:04 PM, Sridhara Gupta Kunjeti
<sridhara at udel.edu> wrote:
> Hi All,
> I am using edgeR for the DE analysis and in the user guide I noticed to use
> the following code:
>
> sum(p.adjust(de.common$table$p.value, method = "BH") < 0.085)
>
> I would appreciate, if I can have some more info on this step.

You are counting the number of genes that have an adjust p-value that
is less that 0.085

> Is this step necessary do it or can we just identify the tags based on p-value?

You are trying to combat the effect of performing a statistical test
multiple times, see:
http://en.wikipedia.org/wiki/Multiple_comparisons#Formalism

> And also what does p.adjust mean here?

It is an easy way to adjust p-values by using one of several "well
known" p-value adjustments, see:

R> ?p.adjust

Google for "multiple test correction" to read up on this a bit more if
you're still confused, or if you're not convinced that adjusting for
multiple testing is necessary.

-steve


> Many thanks!
> Sridhara
>
> --
> Sridhara G Kunjeti
> PhD Candidate
> University of Delaware
> Department of Plant and Soil Science
> email- sridhara at udel.edu
> Ph: 832-566-0011
>
>        [[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
>



-- 
Steve Lianoglou
Graduate Student: Computational Systems Biology
 | Memorial Sloan-Kettering Cancer Center
 | Weill Medical College of Cornell University
Contact Info: http://cbio.mskcc.org/~lianos/contact



More information about the Bioconductor mailing list