Statalist,
I am using the -mim- command in conjunction with -svy:logit- and was asked
to produce a pseudo R2 for my models. After coming to the conclusion that
neither the -mim- or -svy- commands allow me to do this I started digging
through the archives and came across this discussion:
http://www.stata.com/statalist/archive/2007-09/msg00476.html
Dr. Richard Williams has provided some useful information in the post
stating, "Pseudo R^2 is computed using log likelihoods, and log likelihoods
assume that cases are all independent of each other. When you have
clustering and the like, cases are not independent, so pseudo R^2 is not
considered appropriate."
No doubt Dr. Williams is correct but I am hoping for citation purposes
someone could point me to an article or text book stating the same.
Best,
Carter
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
