Ralf,
> I want to make a group analysis using a fixed effect model. Because of
> the small sample sizes (7 and 4 subjects) the random effect toolkit is
> not adequate (very small df). So I put all subjects in one big model
> (one session per subject using the same model).
> Now my question: When I make contrasts between the groups is it
> necessary to
> weight the contrasts (11/2 = 5.5, contrast weights 1.4 and 0.8 for the
> individual subjects in the two groups respectively, the contrast vector
> is simplified 1.4 1.4 ... -0.8 -0.8 ...) or not (1 1 ... -1 -1) ? Is
> this is a valid approach
> or is their a correction for different dfs necessary and how can I
> perfom that ?
What you want to compare are the means of each sample, so just
think of the contrast as doing that. So, if the order of the design matrix
has the 7 subject group first (followed by the 4 subject group), the
contrast should be scalar multiple of
[1/7, 1/7, 1/7, 1/7, 1/7, 1/7, 1/7, -1/4, -1/4, -1/4, -1/4] .
To avoid roundoff errors, you could multiply by the least common denominator:
[4, 4, 4, 4, 4, 4, 4, -7, -7, -7, -7] .
Sincerely,
Eric
>
> TIA
>
> Ralf
>
> --------------F935FE04360FCE82B9A32BA9
> Content-Type: text/x-vcard; charset=us-ascii;
> name="ralf.veit.vcf"
> Content-Description: Card for Ralf Veit
> Content-Disposition: attachment;
> filename="ralf.veit.vcf"
> Content-Transfer-Encoding: 7bit
>
> begin:vcard
> n:Veit;Ralf
> tel;fax:07071/295706
> tel;home:07071/369952
> tel;work:MEG-Centre 07071/2987716
> x-mozilla-html:FALSE
> org:University of Tuebingen;Institute of Medical Psychology and Behavioral Neurobiology
> version:2.1
> email;internet:[log in to unmask]
> title:
> adr;quoted-printable:;;Gartenstr. 29=0D=0A;72074 Tuebingen;;;
> x-mozilla-cpt:;288
> fn:Ralf Veit
> end:vcard
>
> --------------F935FE04360FCE82B9A32BA9--
>
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|