Hi terdon, You are absolutely right. I apologize for any inconvenience my lack of coffee might have caused :-)
I simulated some p-values with the length of your vector and ran the p.adjust() function on them. Here is what I got: system.time(res <- p.adjust(pv, method = 'fdr')) user system elapsed 184.529 4.862 192.066 If you wish, I can run that for you on my machine. Below is my sessionInfo() R version 2.11.1 Patched (2010-05-31 r52180) x86_64-apple-darwin9.8.0 locale: [1] en_US.UTF-8/en_US.UTF-8/C/C/en_US.UTF-8/en_US.UTF-8 attached base packages: [1] stats graphics grDevices utils datasets methods base other attached packages: [1] multtest_2.6.0 Biobase_2.8.0 loaded via a namespace (and not attached): [1] MASS_7.3-7 splines_2.11.1 survival_2.36-2 tools_2.11.1 Best, Jorge On Tue, Mar 8, 2011 at 10:37 AM, terdon <> wrote: > Hi Jorge, and thanks for your answer, it looks promising. > > However, I have a question. First of all, I am a lowly biologist so please > excuse any horrible errors of understanding I may make. > > So, the BH correction depends on, among other things, sorting the vector of > P-values from the smallest to the largest and then multiplying each value > by > the length of the vector times its rank. > > If I understand correctly, your suggestion is to use p.adjust on a subset > of the vector pv, set the n parameter to the length of the entire vector > and > then iterate until all P-values have been adjusted. > > Wouldn't I still need to know the rank of each p value in the subset > vector > with respect to its position in the original sorted vector? I can see how > to > calculate that of course, but how can I give this info to p.adjust if it > only takes the length of the vector as an argument? > > Thanks again > > -- > View this message in context: > http://r.789695.n4.nabble.com/Multiple-testing-corrections-on-very-large-vector-tp3341398p3341615.html > Sent from the R help mailing list archive at Nabble.com. > > ______________________________________________ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
