Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

RE: st: RE: Maximum likelihood estimation of tobit and probit


From   "Julian Fennema" <j.a.fennema@hw.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   RE: st: RE: Maximum likelihood estimation of tobit and probit
Date   Wed, 17 Mar 2004 19:12:57 -0000

Dear Janet,

Sorry, I was not clear enough. The code can do either the original Cragg
model where the two errors are assumed to be independent, or the
extension made by Jones amongst others that they are correlated. For
this see

Jones, Andrew "A Note on the Computation of the Double-Hurdle Model with
Dependence...", Bulletin of Economic Research 44:1, 1992, pp. 67-74

Julian


-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Janet Phiri
Sent: 17 March 2004 19:02
To: statalist@hsphsun2.harvard.edu
Subject: RE: st: RE: Maximum likelihood estimation of tobit and probit


Thanks Julian for this information.

However, the errors in the two equations are assumed to be correlated.
This 
is a case of child labor and schooling. So the two decisions are
different 
but potentailly jointly determined. I want the child schooling to be a 
probit but the child labor to be a tobit (modeling hours of work)
instead of 
it being another probit (you work=1 or do not work=0). I have experience

with estimating bivariate probit models (two probit equations) but not
where 
a probit and a tobit are estimated simultaneously. May be it is some
type of 
a seemingly unrelated regression.

Anyone else out there who can help or who has done something similar?

Thanks,
Janet

>From: "Julian Fennema" <j.a.fennema@hw.ac.uk>
>Reply-To: statalist@hsphsun2.harvard.edu
>To: <statalist@hsphsun2.harvard.edu>
>Subject: st: RE: Maximum likelihood estimation of tobit and probit
>Date: Wed, 17 Mar 2004 18:22:16 -0000
>
>Dear Janet,
>
>It sounds like you may be referring to a Cragg-type double hurdle 
>model, where the probit determines whether the censored dependent 
>variable can be observed or not.
>
>If this is indeed the case, I have coded this and it can be downloaded 
>at the following site: http://www.som.hw.ac.uk/somjaf/stata.htm
>
>Hope that this is what you are looking for.
>
>Julian
>
>-----Original Message-----
>From: owner-statalist@hsphsun2.harvard.edu
>[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Janet Phiri
>Sent: 17 March 2004 18:15
>To: statalist@hsphsun2.harvard.edu
>Subject: st: Maximum likelihood estimation of tobit and probit
>
>
>Hello,
>
>Does anyone know how I can estimate a simultaneous equation of a tobit 
>and a probit in Stata? That is, instead of a bivariate probit, do a 
>similar estimation but for a tobit and probit equation. I read 
>something like that
>in a World Bank Review paper but I am not sure how do the estimation.
>
>Thanks.
>Janet
>
>_________________________________________________________________
>FREE pop-up blocking with the new MSN Toolbar - get it now! 
>http://clk.atdmt.com/AVE/go/onm00200415ave/direct/01/
>
>*
>*   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/
>
>*
>*   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/

_________________________________________________________________
All the action. All the drama. Get NCAA hoops coverage at MSN Sports by 
ESPN. http://msn.espn.go.com/index.html?partnersite=espn

*
*   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/

*
*   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