[BioC] gcrma and signal detection p-values

[Naomi Altman]

What you are asking is contradictory.  The P/M/A calls and p-values 
are intimately connected with MAS 5.0. Many people use these values 
for detection even though they might used other normalizations - the 
p-values are based on a test of PM-MM>0 on a probewise basis and are 
not based on the probeset summaries which are the final output of MAS 
5.0, RMA and gcrma.

This topic has come up before on this list, so you might want to 
search the archives for previous discussion and pointers to references.

--Naomi


At 11:33 AM 3/20/2006, Triantafyllos Paparountas wrote:
>I am trying to get the significance p-value of the signal detection 
>after I have run a gcrma bg correction and normalization.
>
>I do not want to use the inline  mas5calls by Bolstad as I suppose 
>this would defy the prior analysis of the gcrma and  sadly I can 
>testify (as its manual suggests) :) that the package panp  by Peter 
>Warren is targeted to HGU133A and HGU133-Plus-2.0 chipsets.
>
>
>Is there any other way to get P/M/A and p-values for the detection 
>call after I have run my gcrma mle on mouse 430 ver 2 chips?
>
>
>
>Triantafyllos
>         [[alternative HTML version deleted]]
>
>_______________________________________________
>Bioconductor mailing list
>Bioconductor at stat.math.ethz.ch
>https://stat.ethz.ch/mailman/listinfo/bioconductor

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