[R] multiple comparisons

Faheem Mitha faheem at email.unc.edu
Sun Feb 27 06:38:11 CET 2000


Dear R people,

I was wanting `canned' routines to do the following in a complete two way
linear model (I think in R/S+ this is of the form y ~ a*b where a and b
are the factors.) 

a) 95% simultaneous confidence intervals for interaction contrasts of the
form \tau_{ik} - \tau{il} - \tau{jkl + \tau{jll (I think this is all
interaction contrasts) using the Scheffe and Bonferroni methods.

b) 95% simultaneous confidence intervals for all pairwise main effect
contrasts of each factor separately using the Sheffe/Bonferroni/Tukey
methods.

I can't see a way to do this in R. If there is one, please let me know. I
also have access to S+, though I try to use R if possible because I have
it on my home computer. (Also, it is free software :-) ). I know there is
a function in S+ called multicomp, but the only documentation I have
available it that which I get when I type ?multicomp, which I find
somewhat cryptic. I don't know if multicomp can handle the situations
about, but if it can, would someone be kind enough to tell me what the
correct syntax for them? Also, it there somewhere where I can find more
detailed information about multicomp?

By the way, there doesn't seem to be a newsgroup for S+. Does anyone know
of a mailing list? I did a web search for multicomp just now, and someone
had asked a question about multicomp (apparently, without getting a reply)
on a mailing list called s-news at wubios.wustl.edu. What is this?

Please excuse the somewhat off-topic stuff about S+.

                                   Sincerely, Faheem Mitha.

-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request at stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._



More information about the R-help mailing list