[BioC] Difference between normalizeWithinArrays and stat.ma

Gordon K Smyth smyth at wehi.EDU.AU
Thu Jul 15 03:33:47 CEST 2004


Print-tip loess normalization in limma is identical to that in sma
(deliberately).  However the limma command accommodates weights while the
stat.ma() does not.

I like sma but it is a no longer under development.  Better to use one of
the BioC packages under active development and support such as marray or
limma.

Gordon

> Dear friends
>
> I have recently migrated to R (8.0) for analysis of microarray data. I
> am doing a loess (print-tip, perhaps scaled) normalization. I find that
> there are 2 options to do this: using normalizeWithinArrays (Limma) and
> stat.ma(sma). I find the objects returned by the two functions are
> different, however the M and A values seem to be the same. Is one
> function preferable over the other? Any feedback regarding this would be
> appreciated.
>
> Thanks and regards,
>
> Saroj



More information about the Bioconductor mailing list