Date:         Tue, 4 Jul 2006 03:30:26 -0400
Reply-To:     Sebastien <sebgogo@HOTMAIL.COM>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Sebastien <sebgogo@HOTMAIL.COM>
Subject:      post hoc test and Aligned Rank Transformation
Content-Type: text/plain; charset=ISO-8859-1

Hi all,
I have experiments with a two-way ANOVA design. The variances are not equal
and I used a non-parametric statistic to test the interaction: Aligned Rank
Transformation (ART) followed by a traditionnal ANOVA on the aligned rank
data. When the interaction is significant, I would like to do a post hoc
test. Is it correct to do a Tukey test on the aligned rank data or is there
a more specific test available?
Thank you.
Sébastien.