|
|
I have a data set in which faculty (N
~ 250) observed students in lab and in clinic
experiences and indicated "yes"
or "no" to having observed a set of 15 skills under planed or
unplanned conditions
Thus we have two binary independent
variables: Lab (Lab vs Clinic) and Planned (Planned vs Unplanned).
Our data set is structured with four
records for each of the faculty and the skills are represents as variables
One faculty's data would look like this
Note that a skill could be observed
in any combination of conditions
For intance I have shown skill 1 observed
by faculty 101 in lab-unplanned and lab-planned .
School ID FacID
Lab
Planned skill1
skill2 skill3
... etc
1
101 1
0
1 0
0
1
101 0
1
0 1
1
1
101 1
1
1 0
0
1
101 0
0
0 1
1
I would like to use the GEE module in
SPSS 16 or 17 to
examine the main effects of Lab and
Planned and their interaction as predictors of observing each skill
I can of course use log regression but
it would NOT adequately represent the data structure
In addition, I may be interested in
controlling for schools (I have about 25 schools and about 5 faculty per
school)
I wonder if some one might have the
syntax handy for the GEE module for this analyses.
Thanks in advance
Bill
William N. Dudley, PhD
Associate Dean for Research
The School of Health and Human Performance Office of Research
The University of North Carolina at Greensboro
126 HHP Building, PO Box 26170
Greensboro, NC 27402-6170
VOICE 336.2562475
FAX 336.334.3238
|
Locked
