Hi all again,
I was reading all the e-mails about this but I'm a little confuse yet.
Rik, when you say to create the [1 0 -1 0] and [0 1 0 -1] (canonical and derivative: before - after) you mean at first level, and then take this 2 contrast to a 2 way anova? Because
1) I have 5 subjects in 5 session each one before treatment, and again the 5 subjects with the 5 session each one after treatment. "Before" and "after" are analyze in different models, each one with the hrf and TD. So I have 10 design matrix with 2 t-contrast for each one (for condition A i.e. [1 0] [0 1]). How can I compare these groups? I want to see whether there is any difference with or without the treatment.
You say to have one design matrix including "before and after" ([1 0 -1 0] and [0 1 0 -1]) for each subject, and then use a 2-way anova?? not a 1-way anova as Stefan said?
2)Where is 2-way anova in the spm2? In basic models I find only one-way anova.
3)Anova is the best way to compare what I want? not pair-t test or anything else?
Thanks again!
Mirta
-----Mensaje original-----
De: Rik Henson [mailto:[log in to unmask]]
Enviado el: Jueves, 16 de Diciembre de 2004 06:44 a.m.
Para: Mirta Villarreal; [log in to unmask]
Asunto: Re: [SPM] 2nd level analysis with F test?
Mirta -
Simply create T-contrasts for [1 0 -1 0] (canonical: before - after) and [0 1 0 -1]
(derivative: before - after) and enter the resulting contrast images into a (two-way)
ANOVA (no constant term; no within subject effects), and evaluate the F-contrast
for the effects of interest.
Rik
----- Original Message -----
From: "Mirta Villarreal" <[log in to unmask]>
To: <[log in to unmask]>
Sent: Wednesday, December 15, 2004 7:08 PM
Subject: [SPM] 2nd level analysis with F test?
Hi all
I want to perform a pair-t-test within a group of subjects before and after some
treatment. The problem is that for the individual analysis I get better results when I see
at the [1 0, 0 1] F contrast (model = hrf + first derivative).
In previous e-mails I was recomend to evaluate the T-contrasts [1 0] and [0 1] at the
individual level first and take them to an ANova model. I did it and it was ok.
But how can I take this two contrast for each group to a pair t-test? I should choose 4
pairs? (pair 1= hrf before tretment, pair 2= TD before, pair 3= hrf after, pair 4= TD
after) or I can use directly the [1 0, 0 1] F contrast and 2 pairs?
I apreciate any clue!
Thanks
Mirta
Mirta Villarreal, PhD
Neuroimage Laboratory
FLENI
Montaņeses 2325 (C1428AQK)
Buenos Aires, Argentina
C1428AQK
Argentina
Phone: 54 11 57773200 ext: 2925
|