Hi, Just a quick question. Irizarry et al. analysed the single concentration chips from this data set (below). But there are also mixes of 50:50 and 75:25 of the 2 RNA sources. Has the relative linearity of the mixes in comparison to the single concentrations been studied and if so what was the outcome (any reference)? http://hajek.stat.ubc.ca/~jochen/stat547/DilutionStudy.html Thanks, Matt

i looked at that data back when i was writing the paper you mention. not enougn room to include the graphs. here are the relevant pictures: http://www.biostat.jhsph.edu/~ririzarr/mixture/ the short answer is that it seems to be close to what you expect. what makes it complicated is that the mixing occurs in the linear scale but the errors are multiplicative. On Mon, 8 Mar 2004, Matthew Hannah wrote: > Hi, > > Just a quick question. Irizarry et al. analysed the single concentration > chips from this data set (below). But there are also mixes of 50:50 and > 75:25 of the 2 RNA sources. Has the relative linearity of the mixes in > comparison to the single concentrations been studied and if so what was > the outcome (any reference)? > > http://hajek.stat.ubc.ca/~jochen/stat547/DilutionStudy.html > > Thanks, > Matt > > _______________________________________________ > Bioconductor mailing list > Bioconductor@stat.math.ethz.ch > https://www.stat.math.ethz.ch/mailman/listinfo/bioconductor >