-fitstat- calls Nagelkerke's R-square something else if I recall right (Cragg-Uhler?). Anyway, I don't believe cluster alters the log-likelihood, which is what Nagelkerke's measure is based on, so there won't be any difference.
-----Original Message-----
From: [email protected]
To: [email protected]
Sent: 3/13/2009 5:40 PM
Subject: st: Nagelkerke measure for logistic regression
Dear all,
After running the following logistic regression analysis with the cluster
option, I need to determine the Nagelkerke index for my model (logistic
hcv bootingever shareworkslast6 dichotageinitiate, cluster(xsite))
May I use fitstat for that? Does this take into account the cluster
option?
Thanks,
/Christian
*
* 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/
*
* 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/