Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: SUR and a system of logit models


From   "David Roodman (DRoodman@cgdev.org)" <DRoodman@CGDEV.ORG>
To   <statalist@hsphsun2.harvard.edu>, <gaofaye@gmail.com>
Subject   RE: st: SUR and a system of logit models
Date   Tue, 29 Apr 2008 09:39:39 -0400

-cmp- can do 1, 2, 3, or more equations with any combination of linear,
tobit, probit, ordered probit variables. It is a "d1" estimator in the
language of -ml-, so it tends to be significantly faster than than
-mvprobit- and -triprobit- ("d0"/"lf") but significantly slower than
-biprobit- and -bioprobit- ("d2").

--David 

-----Original Message-----
1) -biprobit- fits ML two-equation probit models  either a bivariate
probit or a seemingly unrelated probit (limited to two equations)
2) -bioprobit- fits ML two-equation ordered probit models - either a
bivariate ordered probit or a seemingly unrelated ordered probit
(limited to two equations)
3) -triprobit- estimates simulated maximum-likelihood three-equation
probit models - either a trivariate probit or a seemingly unrelated
probit (limited to three equations), using the GHK smooth recursive
simulator
4) -mvprobit- estimates M-equation probit models - either a multivariate
or a seemingly unrelated probit, by the method of maximum simulated
likelihood (MSL)
I know that logit is not the same as probit, but I usually don't mind
the difference :-) 
Otherwise you can have a look at -cmp- (all programs should be available
from SSC but the first which is built-in the Stata version which I use -
version 9.2); use -findit- to check for the remaining commands)

Warning: I didn't set Statalist-disturbing automatic replies. Thus
please note in advance that I will be offline for the next 8 days at
least, and thus unable to continue this discussion for a while.
Nicola

At 02.33 26/04/2008 -0400, "F. Gao" wrote:
>Dear all,
>
>I could not find reference on the following. Your help is greatly
appreciated.
>
>What to do if I have a system of logit models (binary dependent
>variables) and wish to do SUR regression?
>eg: Pr(A=1)=f(x,y), Pr(B=1)=f(x,z) 



*
*   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/



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