Frequently Asked Questions about MLwiN
Can you suggest naming schemes for variables?
In MLwiN you may create a number of variables that are similar, but
different. For example, say that you have a variable called iq and
your data is at 2 levels, student level and school level. Here is a
suggested naming scheme for your variables at level 1 and level 2.
- Level 1
IQ - Original Variable
IQGrpCen - Center "iq" about the group mean (i.e. each students "iq"
score minus the mean "iq" for the student's school)
IQGrdCen - Center "iq" about the grand mean of IQ (i.e. each
students "iq" score minus the grand mean of "iq")
- Level 2
MeanIQ - No centering (just take the mean of "iq" for each group)
MeanIQGrdCen - Center "iq" about the grand mean (like above) and
then take the mean of that variable for each group).
It is possible that you might have all 5 versions of this
variable in one data file. By choosing a consistent naming scheme,
you can differentiate between the different variables.
UCLA Researchers are invited to our Statistical Consulting Services
We recommend others to our list of Other Resources for Statistical Computing Help
These pages are Copyrighted (c) by UCLA Academic Technology Services
The content of this web site should not be
construed as an endorsement of any particular web site, book, or software
product by the University of California.
