Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: differences between experimental variables with clogit


From   "Claudia Freese" <C.Freese@fh-osnabrueck.de>
To   statalist@hsphsun2.harvard.edu
Subject   st: differences between experimental variables with clogit
Date   Wed, 02 Dec 2009 15:35:58 +0100

Dear Statalist, I am running a Discrete Choice experiment with 4 different brands. One experimental variable I am interested in is the presence or absence of an additional label. Stata gives me for every brand with the additional label a significant value, but z-values for the brands are very close to another. Is there a test I can use to find out if the interaction effects of brand and label are different from one another? Could I - for example - use the LR-test estimating one model with the generic variable label against a second one with the brand-specific label?
Thanks,
Claudia
*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index