Date:         Fri, 5 Mar 2010 15:43:43 +0100
Reply-To:     Marta García-Granero <mgarciagranero@gmail.com>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Marta García-Granero <mgarciagranero@gmail.com>
Subject:      Re: GLM Univariate
In-Reply-To:  <343754.81549.qm@web76112.mail.sg1.yahoo.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed

Eins Bernardo wrote:
> Marta wrote:
> >>>Post hoc tests focus on pairwise differences between means, while the
> overall F tests whether there is any difference among any pair of
> combination of means. For instance, the F could be significant because
> mean1+mean2 combined differ significantly from mean3+mean4 combined. No
> post hoc test would reveal that.
>
> Is the posthoc you are referring to is true also to post hoc in
> one-way anova?
>
Beg your pardon? I don't understand the question. Anyway, what I said
about "classical post-hoc tests" (Tukey ...) is true for any ANOVA
design (ONEWAY, nested, repeated measures...).

Marta

=====================
To manage your subscription to SPSSX-L, send a message to
LISTSERV@LISTSERV.UGA.EDU (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD