Date: Sun, 25 Sep 2005 12:57:22 +0200
Reply-To: Marta García-Granero
Sender: "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From: Marta García-Granero
Organization: Asesoría Bioestadística
Subject: Re: HOV assumption in ANOVA (was Re: SPSS Contacts-Juan]
Content-Type: text/plain; charset=ISO-8859-15
CCS> I would like to determine whether a variable has significant group
CCS> differences (among 4 groups). The variable does not meet the assumption
CCS> of homogeneity of variance.
Use a robust test like Welch or Brown-Forsythe, followed by a post-hoc
like Tamhane's T2 test.
CCS> I was told that there can be adjustments
CCS> made so the variable meets this assumption. Would anyone know how this
CCS> adjustment can be made on SPSS?
The adjustment depends on the nature of the variable and the cause of
the lack of HOV. Sometimes, a log transformation could work, sometimes
not. I think it's better to use robust tests thatn start playing with