[BioC] Limma B statistic

[Darlene Goldstein]

Sabrina AT Case <hxs61 at ...> writes:

> 
> Hello, all
> I am using Limma for my array analysis. Based on the user's guide, I
> canconvert B value to probability.
> however, in my results, I have adj.P.Val of 0.007 with B negative. If
> I use the conversion, the probability will be 0.25. But when you look
> at the p value, it passed the significant 0.05 level. How can I
> explain that? Did I misunderstand some points? Thanks
> 
> Sabrina
> 
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at ...
> https://stat.ethz.ch/mailman/listinfo/bioconductor
> Search the archives:
http://news.gmane.org/gmane.science.biology.informatics.conductor
> 
> 

hi, It looks to me like you are confusing the p (or adj p) value with the B-stat
probability. The (adj) p-value reported in the topTable function is associated
with the mod-t statistic and is not related to the B-stat probability. The
B-stat probability is obtained by converting the log odds ratio to obtain the
probability p.

Does this clear up your question?

Best regards,

Darlene

-- 
Darlene Goldstein
École Polytechnique Fédérale de Lausanne (EPFL)
Institut de mathématiques
Bâtiment MA, Station 8        Tel: +41 21 693 0528
CH-1015 Lausanne              Fax: +41 21 693 4303
SWITZERLAND