[BioC] Simple questions about p values adjustment in limma/multt est

Ramon Diaz-Uriarte rdiaz at cnio.es
Fri Aug 22 11:14:57 MEST 2003

Dear Fai,

> Is the FDR assumed to be a certain percent (e.g. 5%) in the FDR adjustment
> for p values? 

No, it is not. When you use multtest you get "adjusted p-values", and thus is 
up to you to choose the cutting point. The meaning of the "adjusted p-value" 
is very well explained in the documentation for multtest (look at  

> p-values the same as/similar to q-values in SAM procedure?

They are related, but are not the same. You can look, for example, at the 
recent paper by Storey and Tibshirani (PNAS, 2003, 100(16): 9440-9445) for 
explanation of q-values and relation to FDR.



> Thanks in advance!
> Best regards,
> Fai
> ________
> Yuk Fai Leung
> Bauer Center for Genomics Research
> Harvard University
> 7 Divinity Avenue
> Cambridge, MA 02138
> Tel: 617-496-7134
> Fax: 617-495-2196
> email: yfleung at cgr.harvard.edu; yfleung at genomicshome.com
> URL: http://genomicshome.com
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at stat.math.ethz.ch
> https://www.stat.math.ethz.ch/mailman/listinfo/bioconductor

Ramón Díaz-Uriarte
Bioinformatics Unit
Centro Nacional de Investigaciones Oncológicas (CNIO)
(Spanish National Cancer Center)
Melchor Fernández Almagro, 3
28029 Madrid (Spain)
Fax: +-34-91-224-6972
Phone: +-34-91-224-6900


More information about the Bioconductor mailing list