It is seldom a good idea to use the _significance_ of a difference as a
surrogate for its magnitude. The reason is that the significance varies
with many irrelevant aspects of the analysis, such as the model and the
sample size. If you have other measures of group similarity, then there
are many hierarchical clustering methods that might meet your needs. Try
?hclust to get started.
Ben Fairbank
-----Original Message-----
From: r-help-bounces at stat.math.ethz.ch
[mailto:r-help-bounces at stat.math.ethz.ch] On Behalf Of bob sandefur
Sent: Tuesday, April 05, 2005 11:39 AM
To: r-help at stat.math.ethz.ch
Subject: [R] Dendrogram for a type unbalanced ANOVA
Hi-
I have about 20 groups for which I know the mean, variance, and number
of
points per group. Is here an R function where I can plot (3 group
example)
something like
| |----- 2
| |-----------|
| | |----- 1
| |
|------|
| |----------------- 3
|
|
0 25 50 75 100
ie 1 and 2 are different at 75% level of confidence
1 2 combined are different from 3 at 25% level of confidence
If this plot is a silly idea can someone point me to a reference for
anything similar?
Thanx
Robert (Bob) L. Sandefur PE
Senior Geostatistician / Reserve Analyst
CAM
200 Union Suite G-13
Lakewood, Co
80228
rsandefur at cam-llc.com
303 472-3240 (cell) <-best choice
303 716-1617 ext 14
______________________________________________
R-help at stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html