Dear all, I would like to use Combat to correct for different batches (extraction date, hybridazation and amplification). In the description there is only on variable for batch, but i can set more then one covariant, so should I use one for batch and the rest as covariants? Thanks you very much

Hi, I'd recommend the following options: 1. Combine the multiple batch variables into 1 variable if your sample size or design allows for it. 2. Do multiple batch adjustments, first adjust for extraction date and use hyb and amp as covariates. Then apply ComBat again with hyb as batch and amp as a cov, etc. 3. I do have a beta version for ComBat that handles multiple batches, but its somewhat untested, so I can't testify to how well it works. If you would like to help me evaluate it, send me an email off the BioC list. Hope this helps! Evan On Nov 23, 2012, at 6:00 AM, bioconductor-request@r-project.org wrote: > Message: 7 > Date: Wed, 21 Nov 2012 20:29:50 +0100 > From: cirruswolke9@googlemail.com > To: "bioconductor@r-project.org" <bioconductor@r-project.org> > Subject: [BioC] ComBat: multiple batch values > Message-ID: <230A915D-249D-420E-8E11-7B290CCC53F4@gmail.com> > Content-Type: text/plain; charset=us-ascii > > Dear all, > I would like to use Combat to correct for different batches (extraction date, hybridazation and amplification). In the description there is only on variable for batch, but i can set more then one covariant, so should I use one for batch and the rest as covariants? > > Thanks you very much [[alternative HTML version deleted]]