R help - Jun 2003 - How to generate a pairwise non-parametric comparison table?

Dear list

I am comparing the results of several different experimental setups. With
kruskal.test() I can test if there is any difference at all in any of them, if I
understand it correctly. But now, when there is a difference, how do I generate
a (half-) table of pairwise comparisons, using e.g. wilcox.test(), to find the
ones where the difference actually occurs.
I guess I don't have to program this by hand, do I?

Thanks,
David

"David Andel" <andel at ifi.unizh.ch> writes:
> Dear list
> 
> I am comparing the results of several different experimental setups. With
kruskal.test() I can test if there is any difference at all in any of them, if I
understand it correctly. But now, when there is a difference, how do I generate
a (half-) table of pairwise comparisons, using e.g. wilcox.test(), to find the
ones where the difference actually occurs.
> I guess I don't have to program this by hand, do I?
You do. Believe it or not, it is pairwise.wilcox.test()

-- 
   O__  ---- Peter Dalgaard             Blegdamsvej 3  
  c/ /'_ --- Dept. of Biostatistics     2200 Cph. N   
 (*) \(*) -- University of Copenhagen   Denmark      Ph: (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk)             FAX: (+45) 35327907