<>
If you want to implement Neil`s proposal, also look at -help nestreg- to
automate the task. The help file has an entry which shows how you can
combine the -xi- prefix with -nestreg-
HTH
Martin
-----Ursprüngliche Nachricht-----
Von: [email protected]
[mailto:[email protected]] Im Auftrag von Neil Shephard
Gesendet: Mittwoch, 18. Februar 2009 17:12
An: [email protected]
Betreff: Re: st: Fwd: Interpreting dummy coded interactions with 3 levels
Can you not compare the reported R^2 or likelihoods (or even AIC or
BIC) for the different models? Perhaps use -lrtest- to do this
"automagically"?
If you're asking how to actually write the commands to define the
models with interaction then see -man xi- (or
http://www.stata.com/help.cgi?xi ).
The following may also be useful...
http://www.ats.ucla.edu/stat/stata/Library/hetreg.htm
http://www.ats.ucla.edu/stat/stata/Library/logit_wgould.htm
Neil
--
"The combination of some data and an aching desire for an answer does
not ensure that a reasonable answer can be extracted from a given body
of data." ~ John Tukey
Email - [email protected]
Website - http://slack.ser.man.ac.uk/
Photos - http://www.flickr.com/photos/slackline/
*
* 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/
