[BioC] Filtering and Multiple Testing
Robert Gentleman
rgentlem@jimmy.harvard.edu
Fri, 17 Jan 2003 13:20:05 -0500
On Fri, Jan 17, 2003 at 12:00:11PM -0600, Jeff Sorenson wrote:
> Just curious .... The genefiltering package doesn't seem to account for
> multiple testing. We have a separate package for that: multtest. Since
> adjustments for multiple testing are essential, are there plans to
> incorporate that functionality into genefilter? Or are most people just
> doing their filtering with the multtest package and not using genefilter
> anymore?
I tend to think of them as separate operations, filtering and
assessment, and for many of the filters there is no p-value to be
adjusted (eg kOverA or gapFilter etc). So, the sort answer is no, but
that is not intended to preclude some useful innovation should
someone want to do it,
Robert
>
> Thanks,
>
> Jeff Sorenson
>
> _______________________________________________
> Bioconductor mailing list
> Bioconductor@stat.math.ethz.ch
> http://www.stat.math.ethz.ch/mailman/listinfo/bioconductor
--
+---------------------------------------------------------------------------+
| Robert Gentleman phone : (617) 632-5250 |
| Associate Professor fax: (617) 632-2444 |
| Department of Biostatistics office: M1B20
| Harvard School of Public Health email: rgentlem@jimmy.dfci.harvard.edu |
+---------------------------------------------------------------------------+