[R] Are multiple range tests (Duncan, Bonferroni, Tukey, ...) available in R?

Peter Dalgaard BSA p.dalgaard at biostat.ku.dk
Fri May 5 11:38:54 CEST 2000


"Rodolfo Canet-Castello" <rcanet at ivia.es> writes:

> Dear friends
> 
> I'm trying to switch to R for my current work, but could not find a 
> more or less direct procedure to perform multiple range tests such 
> as LSD, Duncan, Tukey, etc after an analysis of variance. I've 
> checked out the documentation, but could not find any useful 
> information for a non-very technical user. Is there any package 
> offering prebuilt procedures to perform such tests? I would 
> appreciate very much any hint.

For one-way anova, pairwise.t.test will do the LSD (aka. "none"),
Bonferroni, Hochberg, and Holm (default) multiple testing adjustments.

I did have some view to other cases when writing it, but didn't get
around to implementing it (yet).

("Other cases" meaning 

	- Scheffe (does anyone ever use those?)
	- Tukey, Duncan, Newman-Keuls, REGW, ... for *balanced* anova
	  effects
        - pairwise testing of contrasts in general regression models

As far as my preliminary analysis went, the results of all of these
procedures can be represented by a table of adjusted p-values, but the
interface issues are not completely trivial.)

-- 
   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
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
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