Date: Tue, 7 Jun 2005 11:07:02 -0700
Sender: "SAS(r) Discussion" <SAS-L@LISTSERV.UGA.EDU>
From: "David L. Cassell" <cassell.david@EPAMAIL.EPA.GOV>
Subject: Re: Multiple comparison
Content-type: text/plain; charset=US-ASCII
"Li,Tom" <Li.Tom@ENDO.COM> wrote:
> Suppose I have 3 treatment groups with placebo, low dose and high
> I use ANOVA's overall F-test to test u0 = u1 = u2 and I just present
> means of the 3 groups and overall p-value from the overall F-test. Do
> still need to do the multiple comparison adjustment? TIA.
If you are *only* showing the overall test p-value, then you are
not doing multiple comparisons. So you don't need that adjustment.
'Multiple comparisons' is used to describe the process when you
test a number of the (usually pairwise) comparisons of means, not
when you only perform the overall F-test and then stop.
YWATF (You're Welcome After The Fact),
David Cassell, CSC
Senior computing specialist