Hi, My problem is as follows: I have a bunch of subjects with a medical condition, and a bunch of normals, and I am looking for differences between the two groups. However, I have several arrays per subject (biological replicates), and so would like to include subject variability into the model. If this was a usual single-response problem, I might use the package "nlme" from R, something like fit <- lme(fixed=response ~ condition, data=mydata, random= ~1 | Subject) Is there something analogous to this in limma? Cheers, Rob.

The subjects are blocks. Have a look at the duplicateCorrelation command and the example for randomized block designs. --Naomi At 06:42 AM 11/10/2005, rob foxall (IFR) wrote: >Hi, > My problem is as follows: I have a bunch of subjects with a >medical condition, and a bunch of normals, and I am looking for >differences between the two groups. However, I have several arrays per >subject (biological replicates), and so would like to include subject >variability into the model. If this was a usual single-response problem, >I might use the package "nlme" from R, something like > >fit <- lme(fixed=response ~ condition, data=mydata, random= ~1 | >Subject) > >Is there something analogous to this in limma? > >Cheers, > Rob. > >_______________________________________________ >Bioconductor mailing list >Bioconductor at stat.math.ethz.ch >https://stat.ethz.ch/mailman/listinfo/bioconductor Naomi S. Altman 814-865-3791 (voice) Associate Professor Dept. of Statistics 814-863-7114 (fax) Penn State University 814-865-1348 (Statistics) University Park, PA 16802-2111

Hi Rob If memory serves me right, limma thinks all replicates are biological replicates, and one can specify technical replicates using the block argument... I think... it's all in the UserGuide that I don't have with me at the moment, but if you open up the PDF and search for "technical replicate" you should find the relevant section. Mick -----Original Message----- From: bioconductor-bounces at stat.math.ethz.ch on behalf of rob foxall (IFR) Sent: Thu 10/11/2005 11:42 AM To: bioconductor at stat.math.ethz.ch Cc: Subject: [BioC] repeated measures in limma? Hi, My problem is as follows: I have a bunch of subjects with a medical condition, and a bunch of normals, and I am looking for differences between the two groups. However, I have several arrays per subject (biological replicates), and so would like to include subject variability into the model. If this was a usual single-response problem, I might use the package "nlme" from R, something like fit <- lme(fixed=response ~ condition, data=mydata, random= ~1 | Subject) Is there something analogous to this in limma? Cheers, Rob. _______________________________________________ Bioconductor mailing list Bioconductor at stat.math.ethz.ch https://stat.ethz.ch/mailman/listinfo/bioconductor