| ![]() |
From | Richard Williams <Richard.A.Williams.5@nd.edu> |
To | statalist@hsphsun2.harvard.edu, statalist@hsphsun2.harvard.edu |
Subject | Re: st: How choose the baseline in gologit2 ? |
Date | Fri, 13 Oct 2006 17:06:47 -0400 |
At 01:00 PM 10/13/2006, mendola wrote:
Dear STATA users, I began to use STATA two months ago and now I am trying to useBecause gologit2 is an ordinal method, the highest category is always the one excluded. You could reverse the coding of the outcome if you wanted the lowest value to be excluded. I don't think it would make sense to exclude one of the intermediate categories.
gologit2. It seems very flexible and moreover very helpful for my research.
I estimated a generalized ordered logit and it seems ok, but I'm not able to find a way
to set my favourite baseline for the response variable (something like baseoutcome()
for mlogit).
It is reasonable to change it or there is some methodological aspect that I'm ignoring?
If it is reasonable, how can I change the default reference level for the outcome
variable?
© Copyright 1996–2025 StataCorp LLC | Terms of use | Privacy | Contact us | What's new | Site index |