Hello, I am new to freesurfer and have created a qdec data table but have a few missing data points for a discrete variable. When using a continuous variable placeholder zeros are used. What should be typed into the table to indicate a data point is missing for a discrete variable? Thank you.
Briana
use
NaN
or
nan
to indicate a missing data point. when a variable is selected as a factor, any subjects with missing data points will automatically be excluded from the analysis.
n.
On Thu, 2010-09-09 at 10:59 -0400, Robustelli, Briana (NIH/NIMH) [F] wrote:
Hello, I am new to freesurfer and have created a qdec data table but have a few missing data points for a discrete variable. When using a continuous variable placeholder zeros are used. What should be typed into the table to indicate a data point is missing for a discrete variable? Thank you.
Briana
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
actually, let me clarify. for missing vars that are continuous, use NaN or nan (not zero). for discretes, there is not an equivalent easy way to indicate missing data. this is a feature i should add (maybe look for the keyword MISSING or something like that), so what i do in these instances is just comment-out that subject in the qdec.table.dat by putting the # char on that subject line. this of course in not very interactive, as you would need to re-edit and restart qdec to change the analysis.
n.
On Thu, 2010-09-09 at 11:20 -0400, Nick Schmansky wrote:
use
NaN
or
nan
to indicate a missing data point. when a variable is selected as a factor, any subjects with missing data points will automatically be excluded from the analysis.
n.
On Thu, 2010-09-09 at 10:59 -0400, Robustelli, Briana (NIH/NIMH) [F] wrote:
Hello, I am new to freesurfer and have created a qdec data table but have a few missing data points for a discrete variable. When using a continuous variable placeholder zeros are used. What should be typed into the table to indicate a data point is missing for a discrete variable? Thank you.
Briana
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
freesurfer@nmr.mgh.harvard.edu
-
Nick Schmansky -
Robustelli, Briana (NIH/NIMH) [F]