Question: DESeq -padj
0
gravatar for Dawei Li
7.9 years ago by
Dawei Li50
Dawei Li50 wrote:
Dear Simon Anders: I am using your DESeq package for data analysis. I have one little quetion regarding the package: In the manual, it is said that padj controls the FDR value. Can I simply call padj as FDR?   My clients want the FDR value. I tell them padj is the FDR value. [[alternative HTML version deleted]]
deseq • 3.7k views
ADD COMMENTlink modified 7.9 years ago by Simon Anders3.5k • written 7.9 years ago by Dawei Li50
Answer: DESeq -padj
0
gravatar for Simon Anders
7.9 years ago by
Simon Anders3.5k
Zentrum für Molekularbiologie, Universität Heidelberg
Simon Anders3.5k wrote:
Hi Dawei On 2011-06-13 14:56, Dawei Li wrote: > Dear Simon Anders: > > I am using your DESeq package for data analysis. > > I have one little quetion regarding the package: > > In the manual, it is said that padj controls the FDR value. Can I simply > call padj as FDR? > > My clients want the FDR value. I tell them padj is the FDR value. > The 'padj' values is what your clients want, however they and you are incorrect in calling them FDR values. An individual test (i.e., a gene) never has an FDR value, it has an adjusted p-values. (Exception: so-called local FDRs, which I am not using here.) The definition of a "p value adjusted for FDR control" is: If one takes all tests (genes) with an adjusted p value below a threshold f, then the list of these genes contains (in expectation) at most a proportion f of false dicoveries, i.e., thresholding adjusted p values at f controls the false dicovery rate (FDR) at f. Hence, the term "FDR" refers to the threshold you cut the adjusted p values at, not to the adjusted p values themselves. Simon
ADD COMMENTlink written 7.9 years ago by Simon Anders3.5k

Dear Simon - Further to your comments on FDR and padj: does that mean that a frequency histogram of padj is invalid as these values refer to a threshold rather than individual values? What I mean is: a histogram of FDRs would be invalid as each FDR value only applies to the list of genes above it in the ranked list (or so I understand) and not to the gene itself. Therefore, does this caveat also apply to padj? 

Regards,
Matt Arno

ADD REPLYlink written 3.8 years ago by matt.arno0
Please log in to add an answer.

Help
Access

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
Powered by Biostar version 16.09
Traffic: 205 users visited in the last hour