[BioC] SAM - survival analysis

Holger Schwender holger.schw at gmx.de
Wed Jul 7 13:46:12 CEST 2004

Hi Willy,

no, there is currently no possibility for a survival analysis with R SAM. It
is only possible to do a one-class or a two-class (paired or unpaired)
analysis using the modified t-statistic and a two-class analysis with
Wilcoxon rank sums. The next version (which will hopefully come out
sometimes around the end of September) will also contain a multiclass
analysis and a SAM method for the analysis of categorical data as SNP data
and (maybe) a possibility for implementing your own d score so that you can
write a function which computes your test score and its null distribution
(the d_bar values) and the rest of the SAM analysis is then done by the
siggenes functions. Sorry, but I'm not very familiar with survival analysis.
So I will not implement this kind of analysis myself.


PS: There is also a possibility to hack the code for the current version of
sam (or more specifically for rs.cal) so that you can do (with some
programming effort) a survival analysis. Let me know if you are interested
in this.

> Hello,
> Thanks for your answers for my previous question.
> Now I'm trying to use the SAM procedure. I known that in Excel it is 
> possible to perform a "censored survival data" analysis but I've noticed 
> nothing similar in R.
> Does this kind of study exist?
> Thanks in advance for your answers.
> Regards,
> Willy
> _______________________________________________
> Bioconductor mailing list
> Bioconductor at stat.math.ethz.ch
> https://www.stat.math.ethz.ch/mailman/listinfo/bioconductor

+++ Jetzt WLAN-Router für alle DSL-Einsteiger und Wechsler +++
GMX DSL-Powertarife zudem 3 Monate gratis* http://www.gmx.net/dsl

More information about the Bioconductor mailing list