Dear Freesurfer's experts,
Would anybody have advice concerning my requests in below mail ?
Thanks in advance.
Best regards, Matthieu
2017-07-01 11:37 GMT+00:00 Matthieu Vanhoutte matthieuvanhoutte@gmail.com:
Dear Freesurfer’s experts,
I would like to test if neuropsychological score across time (continuous time-varying covariate) has an effect on metabolism maps. However, I don’t manage to understand how to define design matrix and contrast associated to assess it with LME models.
I picked up from one former mailing list discussion including Jorge:
*we recommended to order the columns of the design matrix in the following way:
Column 1: the intercept term (which is a column of ones)
Colum 2: the time covariate if it varies across subjects (eg. time from baseline)
Column 3-q: any time-varying covariates (eg. training: 0 before training, 1 after training)
Column q+1-r: the group covariates of interest (eg. a binary variable indicating whether or not the subject is a patient), for n groups you will have n-1 binary covariates
Column r+1-s: interactions between group covariates with the time-varying covariates (only the interesting interactions)
Column s+1-p: any other nuisance time-invariant covariates (eg. age-at-baseline, gender, etc...)*
- If I apply these advices, I would define in Column 3 my
neuropsychological scores as my time-varying covariate but should I have to normalize these scores ?
- If I want to correlate my metabolic maps (inputs) with my
neuropsychological time-varying covariate should I have to define a column of interaction between neuropsychological time-varying covariate and (group or time) ?
- How should I define contrast matrix to assess this effect ?
Thank you for your advices !!
Best regards, Matthieu