Gang,
Thank you for your response.
Yes, now running the post-hoc tests for;
scan1_Group1_vs_Group2
scan2_Group1_vs_Group2
using independent t-tests, I get the same results as 3dMVM. However if I do paired t-tests I get different results from:
group1_Scan1_vs_Scan2
group2_Scan1_vs_Scan2
Is this because of the degrees of freedom? Its only 12 (13 subjects) If I run the paired t-test, but ~24 with two contrasts above.
I have a few more quesitions.
I reran the same dataset using LME, I don't have the discrepancy anymore. The lme post-hoc results in R match my 3dLME results and mixed model results from SPSS (compound symmetry). Why the difference?
Regarding, Type III option in 3dLME vs. 3dMVM.
With 3dMVM, my type III mainF results for 3dMVM match my Type I 3dLME mainF results. If I run the same analysis in SPSS, my Type III mainF SPSS results match my 3dLME mainF results. Why the difference? Are Type III's different for 3dMVM and 3dLME?
Thanks again,
Michael