R-beta: Re: Post-hoc tests

Jim Lemon bitwrit at ozemail.com.au
Thu Jul 16 12:12:26 CEST 1998


Matt,

Here's a Bonferroni-corrected multiple one-sample t-test that I wrote
some years ago.  It took a while to get it into R, as na.omit doesn't
seem to handle vectors and I had to write a quick kludge (na.remove). 
Another more general point was that I discovered that the help page for
t.test gives the name "parameters" for the degrees of freedom, as in S. 
However, the name is really "parameter" as I found after quite a bit of
head-scratching and messing around.

I have some rank-order tests which are similar, and I will see if I can
dig them up as well.  These (and the above) were all written to test
comparisons of the form "which groups are significantly different from
the average of all groups?", which may not be what you are looking for,
but I would be glad to modify them if I can.

Jim
-------------- next part --------------
A non-text attachment was scrubbed...
Name: bost.tar.gz
Type: application/x-gzip
Size: 2673 bytes
Desc: not available
Url : https://stat.ethz.ch/pipermail/r-help/attachments/19980716/6b6eec8c/bost.tar.gz


More information about the R-help mailing list