Hi AFNI experts,
My experiment had one between-subject continuous variable (Score) and one within-subject variable (Time) and used 3dLME to see their interaction. The model failed (see the message below). I think that the problem came from the interaction term (glt 4-6) but had no idea how to modify it. Besides, Any suggests are welcomed. Thanks!
Veda
3dLME -prefix ScorexTime -jobs 6
-model "ScoreTime"
-ranEff ‘~1’
-qVars “Score”
-qVarCenters “0”
-SS_type 3
-num_glt 6
-gltLabel 1 ‘t1’ -gltCode 1 'Time : 1t1’
-gltLabel 2 ‘t2’ -gltCode 2 ‘Time : 1t2’
-gltLabel 3 ‘t3’ -gltCode 3 'Time : 1t3’
-gltLabel 4 ‘Score*(t1-t2)’ -gltCode 4 ‘Time : 1t1 -1t2 Score : 1Score’ \ # the effect of score is larger in Time1 than Time2
-gltLabel 5 'Score(t1-t2)’ -gltCode 5 ‘Time : 1t1 -1t3 Score : 1Score’ \ # the effect of score is larger in Time1 than Time3
-gltLabel 6 'Score(t2-t3)’ -gltCode 6 ‘Time : 1t2 -1t3 Score : 1*Score’ \ # the effect of score is larger in Time2 than Time3
-dataTable
Subj Time Score InputFile
s1 t1 2.787 s1_REML+tlrc’[28]’
s2 t1 -13.213 s2_REML+tlrc’[28]’
.
s1 t2 2.787 s1_REML+tlrc’[31]’
s2 t2 -13.213 s2_REML+tlrc’[31]’
.
s1 t3 2.787 s1_REML+tlrc’[34]’
s2 t3 -13.213 s2_REML+tlrc’[34]’ \
Possible reasons:
0) Make sure that R packages nlme and phia have been installed. See the 3dLME
help documentation for more details.
1) Inappropriate model specification with options -model, or -qVars.
2) In correct specifications in general linear test coding with -gltCode.
3) Mistakes in data table. Check the data structure shown above, and verify
whether there are any inconsistencies.
4) Inconsistent variable names which are case sensitive. For example, factor
named Group in model specification and then listed as group in the table hader
would cause grief for 3dLME.
** Error:
Quitting due to model test failure...