"1) Is it possible to generate a DM of 2x2 within subject ANOVA the way Dr. Penny did?"
It doesn't really matter if you can't generate a design matrix exactly like Dr. Penny's. The more fundamental question is whether you can generate one which is _equivalent_ to Dr. Penny's.
Penny's model includes the following effects, and no others:
* effect of subject
* main effects of A and B
* interaction of A and B
There are many design matrices which instantiate that model. Those matrices are not identical, but they still represent the same model, and in that sense are equivalent.
You can create such a model by using flexible factorial.
|