? bug in limma classifyTestsP
1
0
Entering edit mode
@kimpel-mark-w-727
Last seen 9.6 years ago
I have noticed that I get exactly the same number of sig. t-tests when using the limma function classifyTestsP when using both methods="none" and methods="fdr". Delving a little deeper, I performed the function p.adjust(fit2$p.value, method="fdr"). Output from this indicates that the p values are indeed being properly adjusted with the fdr method. Why are these adjusted p values not being passed to the classifyTestsP function? Thanks, Mark Mark W. Kimpel MD Official Business Address: Department of Psychiatry Indiana University School of Medicine Biotechnology, Research, & Training Center 1345 W. 16th Street Indianapolis, IN 46202 Preferred Mailing Address: 15032 Hunter Court Westfield, IN 46074 (317) 490-5129 Home, Work, & Mobile 1-(317)-536-2730 FAX
limma limma • 730 views
ADD COMMENT
0
Entering edit mode
@gordon-smyth
Last seen 1 hour ago
WEHI, Melbourne, Australia

I am guessing that you only have one contrast in your linear model, in which case classifyTestsP() doesn't do any p-value adjustment. classifyTestsP does adjustment over contrasts, not over genes.

Note that decideTests and topTable are the main user-level functions and you should use them instead of classifyTestsP. Low level functions like classifyTestsP() don't have any advantages -- I have documented them only for completeness.

Gordon

ADD COMMENT

Login before adding your answer.

Traffic: 777 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6