An embedded and charset-unspecified text was scrubbed... Name: not available Url: https://stat.ethz.ch/pipermail/bioconductor/attachments/20080409/ 6602a97b/attachment.pl

Hi Nigel, Limma models the log-ratio (log(Cy5/Cy3)) between the two channels; the columns of 1's mean that you include a constant (an intercept) in your model that has to be added to the mean whatever level of your other factors (time, treatment, you name it...) you have, i.e even if you had the same conditions on Cy5 and Cy3 that effect would still be there. Which means it is the dye-effect! Claus Ng Stanley wrote: > Hi, > > In chapter 8.1.2 Dye swaps, why does appending a column of "1"s as part of > the design matrix take into account the dye effect ? How does limma know > this column of "1"s is for the dye-effect and not some other variablity ? I > can argue that "1"s could represent time effect, and time effect occur. > > Thanks > Stanley > > [[alternative HTML version deleted]] > > _______________________________________________ > Bioconductor mailing list > Bioconductor at stat.math.ethz.ch > https://stat.ethz.ch/mailman/listinfo/bioconductor > Search the archives: http://news.gmane.org/gmane.science.biology.informatics.conductor > > > > > > > Click link below to report this email as spam. > https://www.mailcontrol.com/sr/LfbPOsYxEWQfdeM5Ynvp06uPr0Mrv8Q0+aWee 1Wmo7!kEDU3tN8wf3HJwbvHyVjNDwp+DyY8zsTSyBdGqJafbiYwhYRZcfmElfwwY7+nRPH yWE672gsfPzPDVR4Gpf9bDOcGee3ZHcjZ6tMTMBamPs5OcJsL!hF8AO0dRVnq1sIy+ykk0 Pzmd7wkPAexOkg8WleOeRFGiOlWQcLMIAU6IvDa8+GUGke! > > > -- ********************************************************************** ************* Dr Claus-D. Mayer | http://www.bioss.ac.uk Biomathematics & Statistics Scotland | email: claus at bioss.ac.uk Rowett Research Institute | Telephone: +44 (0) 1224 716652 Aberdeen AB21 9SB, Scotland, UK. | Fax: +44 (0) 1224 715349