[BioC] RMA vs. MAS5

[Naomi Altman]

There is no p-value associated with an expression estimate from RMA.  It is 
a statistical method, so I guess in principle one could be computed using 
some type of resampling method but it is not currently available.

I have looked at the difference between the MAS5 p-value and thresholding 
the RMA expression level at some low number like log(50) or log(32).  The 
differences are fairly substantial.  For that matter, the genes which are 
"significantly differentially expressed" also substantially differ with the 
normalization/summary method.

--Naomi

At 02:26 PM 8/22/2005, Devarajan, Karthik wrote:
>Hello
>
>Does anyone have any experience comparing data quality (expression
>estimates) between RMA and MAS5, in terms of Present/Absent calls? Also, is
>there a way to obtain p-value associated with an expression estimate
>directly from RMA?
>
>Thanks,
>KD
>
>
>
>
>
>
>
>         [[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
Bioinformatics Consulting Center
Dept. of Statistics                              814-863-7114 (fax)
Penn State University                         814-865-1348 (Statistics)
University Park, PA 16802-2111