Michael Rennie wrote:
Hi Paul,
Short answer is you don't. Instead, you estimate your adjusted means,
and then compare adjusted means using one of a couple of different
options- Quinn and Keough (2002, Experimental design and data analysis
for biologists) suggests then using specific comparisons of the
adjusted means using planned contrasts (see page 353), followed by and
adjustment of your alpha for the # of comparisons if necessary. Sokhal
and Rohlf suggest using another method that requires the use of
statistical tables. Either way, the equations can easily be programmed
into R. I prefer the Q&K method as it's pretty straightforward, and
have coded it in R myself. I can send you some code based on the fly
example in Q&K if you're interested.
Mike
[email protected] wrote:
Message: 118
Date: Thu, 25 Mar 2010 19:48:28 -0400
From: Paul Simonin<[email protected]>
To: R Help Listserve<[email protected]>
Subject: [R] Tukey test on ANCOVA
Message-ID:<[email protected]>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Greetings!
I have one quick question: How do you do a Tukey test on an ANCOVA?
Thanks for any tips!
-Paul
------------------------------
______________________________________________
[email protected] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
