Dear Yuki Chen
> 1). For the one-sample t-test, I selected one subject1_con_0001.img,
> 2). For the two sample t-test, I selected subject1_con_0001.img and
> subject2_con_0001.img, and I entered [1 -1] for the "[2]group"
I'm not really sure, that I understand, what you have done.
Have you selected only one image for the one-sample t-test?
If so, this will explain the error. You can not do statistics by using only one image for the one sample t-test and only two images for a two sample t-test.
The meaning of 'sample' is, that you want to compare populations. This means: the one sample t-test will show you the main effect within a population. The population is defined by, for example, all '*con_0001' images of all subjects.
The same with the two sample t-test. Here you compare two populations and test for the differences between them. For example all '*con_0001' images from one group against all '*con_0001' images from another group.
Does this help?
Good luck,
Karsten
----------------------------------
Karsten Specht
fMRI Section
Department of Neuroradiology
Medical Center Bonn
Spessartstrasse 9
53119 Bonn
Germany
Phone: ++49-(0)228/90 81-178
Fax: ++49-(0)228/90 81-190
E-Mail: [log in to unmask]
WWW: http://www.mcbonn.de/Praxis/praxis15/fmri1.htm
|