Hi,

I am trying to run a multivariable GLM with mri_glmfit and I am currently setting up my fsgd file. I have 9 binary variables and 1 continuous variable. My understanding is that in the fsgd file, my "class" would be every possible combination of these binary variables - which is a lot (hundreds) and setting this up manually doesn't seem reasonable. Is this correct and if so could you recommend another way to run this analysis?

Thanks,

Amanda