Dear Andrew and Karl,
In a recent message concerned with random analysis, you cite the "Worsley seminal 1991 paper" , but in an older discussion (11 Nov 97, reply to Van Horn) it was the "seminal 1992 paper". I just wondered if you referred to two different papers, or only to the last one of those two:
**Worsley, K.J., Evans, A.C., Strother, S.C. and Tyler, J.L. (1991). A linear spatial correlation model, with applications to Positron Emission Tomography. Journal of the American Statistical Association, 86:55-67.
**Worsley, K.J., Marrett, S., Neelin, P., and Evans, A.C. (1992). A three-dimensional statistical analysis for CBF activation studies in human brain. Journal of Cerebral Blood Flow and Metabolism, 12:900-918.
More up to date, I had a contradictory discussion about the comparisons between random effect analysis (as you proposed in the HBM98 poster) and the use of a conjunction analysis between individual subjects two-conditions comparisons results, each subject being considered as a study in a multi-study multi-conditions design (SPM96). My understanding is that with the latter you save (a lot!) degrees of freedom for the analysis, thus increasing your statistical power, but that it cannot be considered truly as a population-level inference, while the random analysis allows for this inference.
My question is: am I wrong? And the additional question is : will SPM99 be more helpful in this sense to both keep more degrees of freedom and address a population-level inference?
Thanks for all comments.
Philippe Peigneux
//// ,,,, ////
--[[. .]]------[* *]------[@ @]--------------
[~] [~] [#]
PEIGNEUX Philippe, Lic. Psych., Chercheur
E-mail: [log in to unmask]
Cyclotron Research Centre - Neurology Unit
Liege University
Batiment B30
Allee du 6 Aout, 8
B-4000 Liege
BELGIUM
phone: +32-4-3662316
fax: +32-4-3662946
Neuropsychology Department
Liege University
Batiment B33
Boulevard du Rectorat, 3
B-4000 Liege
BELGIUM
phone: +32-4-3662394
fax: +32-4-3662808
---------------------------------------------
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|