[BioC] limma - RG.MA

[Gordon K Smyth]

> Date: Fri, 16 Dec 2005 21:06:57 -0500
> From: Naomi Altman <naomi at stat.psu.edu>
> Subject: [BioC] limma - RG.MA
> To: bioconductor at stat.math.ethz.ch
>
> Shouldn't RG.MA be:
>
> function (object)
> {
>      object$R <- 2^((object$A + object$M)/2)
>      object$G <- 2^((object$A - object$M)/2)
>      object$M <- NULL
>      object$A <- NULL
>      new("RGList", unclass(object))
> }
>
> 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

No, the code is correct as it is.  Don't forget that A=(logR+logG)/2 involves a factor of 2 in its
definition while M=logR-logG does not.  Hence only M is divided by 2 in the reverse computation.

Best wishes
Gordon