Dear Philippe,
> Thank you very much for your quick (and encouraging) reply. I think I
> have now good arguments to discuss the problem with the editor.
> However, I'm not sure if the reviewer is or not familiar with the
> standard models in PET analysis. Actually, he quote a chapter's book
> that I was unfortunately unable to consult:
>
> Woods, Iacobini, Grafton, Mazziotta. Improved analysis of functional
> activation studies involving within-subject replications using a
> three-way ANOVA model. In : Quantification of Brain Function using PET,
> Myers, Cunningham, Bailey, Jones (Eds), Academic Press, San Diego, CA,
> 1996, pp. 353-358.
>
> Do you know about this technique ? I don't know if it represent a
> standard for people who use other statistical packages than SPM or if
> it is a new proposal that the authors have done in this chapter. I
> think it will be helpful for me to know it before presenting my
> arguments to the editor.
This is an chapter following a meeting many years ago in Akita, Japan.
The Anova model desicribed is simply a variant of the general linear
model used by SPM and as such could be implemented easily within SPM.
The issue here is not about methodology or sorftware implementation but
simply the choice of statistical model. You are already using a
one-way Anova in your original analysis. Including subject by
condition interactions would make it a two-way Anova. Including the
replication factor and all interactions would make it a three-way
Anova. The last extension may be justified if you thought replication
effects were important but in most analyses they are ignored. The
issue then reduces to your choice of model. I repeat that if your
simpler model is sufficient then everything is fine.
With best wishes - Karl
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|