[BioC] tagwise parameters for negative binomial distribution in edgeR

[Yunshun Chen]

Dear Davide,

I'm not sure what you meant by "identify tagwise outliers".
Are you interested in finding genes having outlier tagwise dispersions? 
If so, you can use the function estimateDisp() with robust=TRUE. 
The detected outlier genes will be given smaller prior.df in the output.

If you use r and p to parameterize the NB distribution, then r=1/phi and
p=(phi*mu)/(1+phi*mu), where phi is the dispersion and mu is the mean.
The values of mu can be obtained from the fitted values in glmFit().


Best wishes,
Yunshun


------------------------------

Message: 23
Date: Wed, 19 Mar 2014 09:33:45 +0100
From: Davide Cittaro <cittaro.davide at hsr.it>
To: "bioconductor at r-project.org list" <bioconductor at r-project.org>
Subject: [BioC] tagwise parameters for negative binomial distribution
	in	edgeR
Message-ID: <B6A4308D-647D-4239-B176-1EB4C7E12FC2 at hsr.it>
Content-Type: text/plain; charset=us-ascii

Dear list, 
I have a DGElist object in edgeR, already processed with calcNormFactors,
estimateCommonDispersion and estimateTagWiseDispersion. Now, I would like to
identify tagwise outliers in my data, I thought I could estimate NB
distribution for each tag. Given that a NB is defined by two parameters (r
and p), I assume that r = 1/x$tagwise.dispersion, how can I get tagwise p
from DGEList dataframe?
Thanks

d


______________________________________________________________________
The information in this email is confidential and intend...{{dropped:4}}