[BioC] SAM siggenes number of permutations

Holger Schwender holger.schw at gmx.de
Wed Jan 30 18:48:29 CET 2008


Just as a side note to Jim's comments: Besides using, e.g., limma to do a parametric test, you can also apply SAM to the genes assuming normality. For that, you have either to program your own test score or run Code Chunk 34 of the R vignette (which defines the function t.stat), and then use

> sam(data, cl, method = t.stat)

Best,
Holger



-------- Original-Nachricht --------
> Datum: Wed, 30 Jan 2008 10:31:17 -0500
> Von: "James W. MacDonald" <jmacdon at med.umich.edu>
> An: olivier armant <olivier.armant at itg.fzk.de>
> CC: bioconductor at stat.math.ethz.ch
> Betreff: Re: [BioC] SAM siggenes number of permutations

> Hi Olivier,
> 
> olivier armant wrote:
> > Dear all,
> > 
> > I try to do SAM on my data using siggenes on R 2.4.1 (I am a beginner)
> > 
> > The function I use is (after creating the vector)
> > sam.out<-sam(data.gcrma, sam.c1, B=100, var.equal=TRUE, Set med=TRUE)
> > 
> > It seems to work well but I get allways the message:
> >  number of effective permutations=20
> > 
> > Does it means that only 20 permutations were done, werheas I ask for 100
> permutations with the function B=100??
> 
> Yes. A more correct statement would be that the number of combinations = 
> 20. You evidently have 6 samples, with 3 in each class. There are only 
> 20 ways you can make two groups of three, so it doesn't matter that you 
> requested B=100.
> 
> > 
> > I read in the SAM excel package from standford that a precise FDR
> requires 1000 permutations!!!What do you think??
> 
> Ideally you want lots of combinations, as the null distribution with 
> only 20 combinations will be very discrete. You can either assume that 
> you are getting a reasonable null distribution with 20 combinations, or 
> you can decide that isn't good enough and make the assumption that the 
> genes all follow a Normal-ish distribution and use a parametric method 
> (e.g., the limma package).
> 
> Best,
> 
> Jim
> 
> 
> > 
> > Help would be welcome
> > 
> > 
> > Olivier ARMANT PhD.
> > 
> > Institute of Toxicology and Genetics
> > Forschungszentrum Karlsruhe
> > Hermann-von-Helmholtz-Platz 1
> > D-76344 Eggenstein-Leopoldshafen
> > Germany
> > 
> >  tel: +49-7247-82-2560
> >  fax: +49-7247-82-3354
> > 
> > 	[[alternative HTML version deleted]]
> > 
> > _______________________________________________
> > Bioconductor mailing list
> > Bioconductor at stat.math.ethz.ch
> > https://stat.ethz.ch/mailman/listinfo/bioconductor
> > Search the archives:
> http://news.gmane.org/gmane.science.biology.informatics.conductor
> 
> -- 
> James W. MacDonald, M.S.
> Biostatistician
> Affymetrix and cDNA Microarray Core
> University of Michigan Cancer Center
> 1500 E. Medical Center Drive
> 7410 CCGC
> Ann Arbor MI 48109
> 734-647-5623
> 
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at stat.math.ethz.ch
> https://stat.ethz.ch/mailman/listinfo/bioconductor
> Search the archives:
> http://news.gmane.org/gmane.science.biology.informatics.conductor

--



More information about the Bioconductor mailing list