[BioC] edgeR continuous variables

[Mark Robinson]

Hi Fredrik,

Short answer is yes -- edgeR GLM will handle continuous covariates.  Correct, there is no case study on this, but it's just another variable/covariate and I guess  categorical variables (designed experiments) are more common.

The logFC in this case is the (log of the) multiplicative effect of a single unit increase in the covariate.  I googled an example (See Slides 7-9):
http://courses.education.illinois.edu/EdPsy589/lectures/4glm3-ha-online.pdf

Hope that helps.

Best, Mark


----------
Prof. Dr. Mark Robinson
Bioinformatics, Institute of Molecular Life Sciences
University of Zurich
http://tiny.cc/mrobin



On 09.01.2013, at 14:47, Fredrik Karlsson wrote:

> Hi,
> 
> How does edgeR handle continuous variables? I would like to include variables like age and BMI in my analysis. As far as I have seen there is no case study in the documentation, please correct me if I am wrong or refer to a place where this is discussed.
> Especially, glmLRT produces a logFC value also for continuous variables if they are included in the design matrix. How is that calculated and does it make sense to do this?
> 
> The reason I want to include this is to correct for e.g. age effects on a metagenome sample set.
> 
> Sincerely,
> 
> Fredrik Karlsson
> 
> Systems and Synthetic Biology
> Department of Chemical and Biological Engineering
> Chalmers University of Technology
> Kemivägen 10, SE-412 96 Göteborg, Sweden
> Office: Room  3057B
> Tel+46(0)31-772 3886
> www.sysbio.se<http://www.sysbio.se/>
> 
> 
> 
> 	[[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