Dear All, I have to deal with an experimental design comprising both categorical (strain A/B) and numeric (time 0/2/4/10) factors. Is Bioconductor offering specific solutions for this? I was looking into the lme function of the nlme package and I was wondering if it was the right choice. Thank you Best, Paco [[alternative HTML version deleted]]

On Fri, Apr 17, 2009 at 4:12 AM, Paco Recca <pacorecca@yahoo.it> wrote: > Dear All, > > I have to deal with an experimental design comprising both categorical > (strain A/B) and numeric (time 0/2/4/10) factors. Is Bioconductor offering > specific solutions for this? I was looking into the lme function of the nlme > package and I was wondering if it was the right choice. > Hi, Paco. You have a short time series, it seems. Your time series is short, though, so you may not end up treating it as such in an analysis. In any case, you probably do not want to treat the time variable as a "number". For details, you might look at the limma package (which can be used to deal with time series data) or at packages, like maSigPro, which are specifically designed for time series data. A quick search of the archives will probably turn up other suggestions. Sean [[alternative HTML version deleted]]