Question: PLINK/SEQ SKAT gives different p-values depending on number of tests run
gravatar for p0078005
7 months ago by
p00780050 wrote:

We are using PSEQ to analyse rare variants at a gene-based level. I like the interface and the output from PSEQ but have noticed that if I run SKAT alone, I get a different p-value from if I run SKAT and (for example) C-alpha in the same line.

The input files are exactly the same, it is just the number of tests run that differ. Can anyone tell me if PSEQ uses a project-wide p-value adjustment by default (this is the only explanation I can think of to explain this).

Thanks DIanne

pseq plinkseq skat • 290 views
ADD COMMENTlink modified 7 months ago by genomax50k • written 7 months ago by p00780050

As far as I know SKAT will return a different p-value every time you run it, regardless of running other tests. But that's the case if you just run SKAT in R. Not sure about PSEQ.

ADD REPLYlink written 7 months ago by WouterDeCoster29k
Please log in to add an answer.


Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
Powered by Biostar version 2.3.0
Traffic: 2067 users visited in the last hour