Hi Doug,
I´m a bit unsure about polynomial fitting with qdec. So I want to demonstrate linear, quadratic and cubic effects of age on lGI. You wrote: If you need to test all 3, then you'll have to use mri_glmfit with and FSGD file.
I want to be sure if it is correct to demonstrate:
1. age linear effects: age linear (for example 12 Years) as continous (covariate)? 2. age quadratic effects: age square (144 Years) as continous (covariate) and age linear (12 Years) as nuisance variable? 3. age cubic effects: age cubic (1728 Years) as continous (covariate) and age linear (12 years) as nuisance variable? Is it neccesary to include age square (144 years) in the model to show only the cubic effects? And if it is neccesary do I need mri_glmfit with a FSGD file or can I add age square (144 Years) as a seocond nuisance variable in qdec?
Best wishes and thanks a lot
Daniel