Gang or other experts,

I thought the 4-way ANOVA type 5 CxD(AxB) should be appropriate for my data with two subject clsasses, one stimulus category: factor A-disease (two levels: patient and control), factor B-sex (two levels: female and male), factor C-stimulus condition (three levels: S1, S2, S3), factor D-subjects, random, nested with both A and B.
This is a balanced design; there are 8 subject data for each subgroup, total 96 dataset.
Following matlab script instruction on the AFNI website, after starting GroupAna, I input all arguments step by step, then got following message:
Total slices along Z axis: 75.
Running analysis on slice:
#1 … ??? Error using = = > horzcat
All matrices on a row in the bracketed expression must have the same number of rows.
Error in = = > SumofSquares.m
On line 266 = = > ….

When I treated the three stimulus separately by using ANOVA 3-way type 2 (AxBxC, A and B as same as above, C is random subject factor), it worked well as expected.
I couldn’t figure out what’s wrong by using 4-way ANOVA.
Thanks a lot.

Jony