Hello, I need some help about 3dRegAna. I am doing a two-way ANOVA with unbalanced data. Below is a sample of my model (columns are factor a, factor b, and axb respectively).
3dRegAna
-rows 39
-cols 3
-xydata 0 0 0 subj1.nii
-xydata 0 1 0 subj2.nii
-xydata 1 0 0 subj3.nii
-xydata 1 1 1 subj4.nii
…
-model 1 2 3 : 0 \
I observed significant axb interaction at a couple of voxel clusters. So, I hope to perform pairwise comparisons to find out the detail. Any suggestion on how to do it?
I tried to type in the script directly into the terminal and the error did not show up. I think it could be some formatting issue of the text. However, it gave me this error:
** Error:
The number of -gltLabel is not consistent with that
specified by -num_glt 2
No matter how many glt I set, it always gave me the error saying the number is not consistent.
I apologize for bothering you again… But I came across a new error message as below:
Error in outList[[1]][[n]] : subscript out of bounds
Calls: process.MVM.opts → gl_Constr
Execution halted
I think the issue is with the line below because everything works well without it.
-num_glt 1
-gltLabel 1 AvB -gltCode 1 ‘group : 1a -1b’ \
My data table looks like
-dataTable
Subj group treat InputFile
s1 a T1 s1_map_z.nii
s2 a T1 s2_map_z.nii
S3 a T2 s3_map_z.nii
S4 a T2 s4_map_z.nii
s5 b T1 s5_map_z.nii
s6 b T1 s6_map_z.nii
s7 b T2 s7_map_z.nii
s8 b T2 s8_map_z.nii
Could you help to see what could be wrong? Thanks.
Thank you so much for the suggestion. It works! I really appreciate your help.
Best,
Shiyu
The
National Institute of Mental Health (NIMH) is part of the National Institutes of
Health (NIH), a component of the U.S. Department of Health and Human
Services.