Hi! I would in a microarray experiment analyze three factors simultaneously in Limma, treatment, group (i.e. gender), and study center. Is it possible to include three factors simultaneously in an interaction model? Can I use the “sum to zero” parameterization as described in Section 8.5.4 of the user guide? Any more specific recommendation on how to proceed? /Ingrid [[alternative HTML version deleted]]

Dear Ingrid, > Date: Thu, 16 May 2013 19:57:37 +0000 > From: Ingrid Dahlman <ingrid.dahlman at="" ki.se=""> > To: "bioconductor at stat.math.ethz.ch" <bioconductor at="" stat.math.ethz.ch=""> > Subject: [BioC] analyze three factors in Limma > > Hi! > I would in a microarray experiment analyze three factors simultaneously > in Limma, treatment, group (i.e. gender), and study center. Is it > possible to include three factors simultaneously in an interaction > model? It's easy to include three, or indeed any number, of factors in a limma model. > Can I use the "sum to zero" parameterization as described in Section > 8.5.4 of the user guide? You could, but why would you want to? > Any more specific recommendation on how to proceed? Hard to give any specific advice on the basis of the information you give. However, if you are not familiar with setting up model formula in R for factorial experiments, then the limma User's Guide strongly recommends that you setup your experiment as a oneway layout as per Section 8.5.2. This works for any number of factors. Best wishes Gordon > /Ingrid ______________________________________________________________________ The information in this email is confidential and intend...{{dropped:4}}