Hi John,

X is the design matrix. The rows are the total number of time points for all subjects, the columns the different parameters of your model.

In the wiki example, the first column is all 1s (intercept) the second is the time_from_baseline and other parameters that are in the matrix M (M was read from the qdec table file), the last column is the interaction between the first and second column in M (so probably time X group interaction).

So for you, you probably have
column of ones, time_from_baseline and potentially other control variables (age_at_baseline, gender, scores? IQ.. whatever you want).
Only having 2 columns (ones for the intercept and time for the slope) allow you to test
- if whatever you test is different from zero (intercept), usually that is the case, as you measure volume or thickness
- if the longitudinal slope is different from zero, usually that is also the case, but sometimes you don't have enough power to find that effect.

So that does not really tell you much. For most interesting questions you need two groups.

Best, Martin

On 03/21/2016 12:40 PM, John Anderson wrote:

Hi Dr Martin
I want to study the change in cortical thickness overtime in one group of subjects.

I have only one group of subjects who scanned multiple times ( two time points and more)

I followed the pipeline exactly as in wiki.

I want to inquire about X in this case . Is it supposed to be 1 ( one group)

In wiki they used the follwoing x=[ones(length(M),1) M M(:,1).M*(:2)] how this formulla will be for one group of subjects?

Bests,
John
_______________________________________________
Freesurfer mailing list
Freesurfer@nmr.mgh.harvard.edu
https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer

-- 
Martin Reuter, PhD
Assistant Professor of Radiology, Harvard Medical School
Assistant Professor of Neurology, Harvard Medical School
A.A.Martinos Center for Biomedical Imaging
Massachusetts General Hospital
Research Affiliate, CSAIL, MIT
Phone: +1-617-724-5652
Web  : http://reuter.mit.edu