Hi Gang,
I'd like to give you a little more details.
Our unstructured (var-cov structure) model is as follows:
-model "DX*VISIT*PHASE*CONGRUENCY+meanFD" -qVars "meanFD" \
-ranEff "~1" \
-corStr "corSymm(form=~1|Subj)"\
Our model with AR1 is:
-model "DX*VISIT*PHASE*CONGRUENCY+meanFD" -qVars "meanFD" \
-ranEff "~1" \
-corStr "corAR1(form=~1|Subj)"\
These models yield identical results for all effects and interactions. The results are, however, different (less extensive) compared to those obtained using the default settings when we do not specify corStr.
It seems that in the 3dLME code, all corStr specifications (no matter what we specify) would default to AR1. The default setting (without specifying anything) is NULL (default in R's lme), which is I believe compound symmetry.
We would like to specify an unstructured matrix since this would be consistent with other ROI based mixed models. We have a large dataset (two groups of both 150+ subjects).
We really appreciate your help in this. Thanks!
Best
Hans