At 02:55 PM 3/5/2004 +0100, Dimova, Ralitza wrote:
Thanks so much!!! I'll try and see how it goes, possibly contact you later
about developmens/ more questions. It would be great if I can compare
coefficients both across the MLOGIT categories (Wald test does this for
the whole coefficient vector, but I am really interested on the effect of
"education" on each category) AND across the years. Good luck with the
handout; hope to be hearing more from you over the next stages....
Not having done much with Mlogit, I don't have a good feel for what the
interesting across-category hypotheses would be. If, for example, the
effect of education was the same on all categories, that would basically
mean that the effect of education was zero, right, i.e. education has no
effect on group membership? If the effect of education was the same for a
subset of categories (which might include all the non-reference groups)
perhaps that would imply that these groups could all be combined together
(at least if education was the only var you were looking at.) Or, perhaps
something like, a higher level of education will make it more likely that
you won't be in the reference group, but where you go instead is just kind
of a random process?
Can anyone offer some specific examples here of the sorts of across-group
hypotheses that would be interesting to test and what exactly they would mean?
-------------------------------------------
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
FAX: (574)288-4373
HOME: (574)289-5227
EMAIL: [email protected]
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
