Hi all,
I have two questions about a 2nd level regression analysis:
1. I would like to use a categorical variable (diagnosis) as a covariate and was wondering if it would be correct to use ones and zeroes for the two diagnoses in a single covariate. Or should I create two separate covariates and code each for a single diagnosis? And how would things change if I have 3 levels of the same categorical variable?
2. If I include two different covariates (one continuous and one categorical), will the contrasts of 0 1 0 and 0 0 1 (corresponding to: scans, covariate 1, & covariate 2) give me the variance associated with each covariate while controlling for the other?
Thanks!
- Amri
|