The SAS PROC POWER procedure has a worked example for binary logistic regression
with multiple predictors.
In my opinion, the problem with power calcs for complex models is not so much the mechanics
of the calculation -- it's the complexity of having the investigator provide the appropriate inputs
to the calculation. You can always try to run a simulation in the absence of other calc tools.
Ever try to get an investigator to give you the presumed correlation between pre and post
measurements in a simple paired t-test calculation?
Hope this helps.
Marty
-------------------------------------------
Martin Lesser, PhD
Director, Biostatistics Unit
Feinstein Institute for Medical Research
Manhasset, NY 11030
-------------------------------------------