[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
Re: st: RE: Re: -ineqdeco- and saving subgroup results
At 02:36 AM 5/24/2006, you wrote:
I am new to STATA and I was wondering what STATA 8 commands are for ordered
and multinomial logit/probit on panel data as well as for post-estimation -
predicted probabilities, marginal effects.
official Stata: ologit, oprobit, slogit (Stata 9 required)
user written: gologit2, goprobit, oglm (the latter is good if you
want to model heteroskedasticity or use links besides logit and
probit; but it requires Stata 9). The goxxx commands allow you to
selectively relax the parallel lines assumption.
Multinomial: mlogit, mprobit (Stata 9)
The predict command with option p will usually compute predicted probabilities.
For marginal effects, there is Stata's -mfx- command. User-written
routines, that are useful when there are more than 2 outcomes,
include -mfx2- and -margeff-.
There are assorted other commands out there for other ordinal
models. -findit ordinal- might show them but for some reason I can't
access Stata's site right now so I am not sure what all shows up.
Also highly recommended: the -spost- routines of Long & Freese. Also
see their book, available from Stata Press. I'd give a link but I
can't get to Stata's site right now.
Richard Williams, Notre Dame Dept of Sociology
OFFICE: (574)631-6668, (574)631-6463
WWW (personal): http://www.nd.edu/~rwilliam
WWW (department): http://www.nd.edu/~soc
* For searches and help try: