[BioC] poe.mcmc - phenotypic label - coding

Debashis Ghosh ghoshd at psu.edu
Thu Oct 6 04:22:08 CEST 2011


Dear Dr. Jonczyk,

It's an error in the text.  Hyungwon should be revising the vignette
in future versions of metaArray.

Debashis

On Tue, Oct 4, 2011 at 8:09 AM, mjonczyk <mjonczyk at biol.uw.edu.pl> wrote:
> Dear List,
>
> I'd like to make sure I understand coding of phenotypic label in
> poe.mcmc function of metaArray correctly.
>
> Vector of my arrays' treatments could be presented as:
>
> (ctrl, ctrl, ctrl, trt1, trt1, trt1) so as NN value I used vector (1,
> 1, 1, 0, 0, 0).
>
> Documentation for either poe.mcmc, poe.em and fit.em say that "1" means
> that e=0 (baseline expression),
> and "0" is for other conditions.
>
> Although this three documentation files suggests the same coding,
> fit.em states that:
> "
> cl: A vector of 0s and 1s. Use 1 for normal phenotype and 0 for
>           non-normal phenotype. Note that
> *this is the opposite of POE MCMC.*
> If all samples are of unknown phenotype or of the same
>           one, give vector of zeros. When class information is
>           provided, conditional estimation of the mixture is applied.
> "
> So is it simply an error in text or should I code my variants
> differently?
>
> Best Wishes!
>
> --
> Maciej Jonczyk,
> Department of Plant Molecular Ecophysiology
> Institute of Plant Experimental Biology
> Faculty of Biology, University of Warsaw
> 02-096 Warszawa, Miecznikowa 1
> Poland
>
>
>
> --
> This email was Anti Virus checked by Astaro Security Gateway.
> http://www.astaro.com
>
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at r-project.org
> https://stat.ethz.ch/mailman/listinfo/bioconductor
> Search the archives:
> http://news.gmane.org/gmane.science.biology.informatics.conductor
>



-- 
Debashis Ghosh
Departments of Statistics and Public Health Sciences
Penn State University
University Park, PA 16802
works.bepress.com/debashis_ghosh/



More information about the Bioconductor mailing list