[BioC] LIMMA: How do I get the standard deviation?

Marcus Davy MDavy at hortresearch.co.nz
Fri Feb 4 04:36:26 CET 2005


Is this what you want for R and G channel simple graphics?

RGnorm <- RG.MA(MA) # on raw scale

# log2 scale standard deviations for each row in R, G matrix
logRsd <- apply(log2(RGnorm$R), 1, sd, na.rm=T)
logGsd <- apply(log2(RGnorm$G), 1, sd, na.rm=T)

 
The error components in lmFit, eBayes fit are for the MA$M fitted values, fit$coef.


Marcus

>>> Sebastian Thieme <Tobar at gmx.de> 4/02/2005 12:21:04 PM >>>
Hello !

To get the intensities of R and G channel I use RG.MA() on normalized data 
set.
I can calculate the standard deviation using simple function sd( ). But 
there  the spot duplicates are not taken into account, only slide replicates.
After running lmFit(), eBayes() and topTable() the duplicates are accounted.
But how can I get from that results the standard deviation?
Does it correspond to $stdev.unscaled from lmFit() output and can I use 
that for simple graphics (like R to G channel with sd-bars)?

Thanks !

Sebastian Thieme

_______________________________________________
Bioconductor mailing list
Bioconductor at stat.math.ethz.ch 
https://stat.ethz.ch/mailman/listinfo/bioconductor

______________________________________________________

The contents of this e-mail are privileged and/or confidenti...{{dropped}}



More information about the Bioconductor mailing list