Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: st: RES: RE: panel tobit with fixed effects
From
Anders Alexandersson <[email protected]>
To
[email protected]
Subject
Re: st: RES: RE: panel tobit with fixed effects
Date
Fri, 23 Mar 2012 17:05:19 -0400
Fernando, the user-written Stata program pantob.ado is at
http://www.princeton.edu/~honore/stata/pantob/pantob.ado.
Anders
On Fri, Mar 23, 2012 at 4:50 PM, Fernando Cunha <[email protected]> wrote:
> Thank you David,
> as Anders said "Honoré (1992) has developed a semiparametric estimator for
> fixed-effect tobit models." He has an available ado file for this named
> pantob.ado at http://www.princeton.edu/~honore/stata/index.html. " But the
> language of this file is gauss. Tobit is a non linear function and the
> likelihood estimator for fixed effects is biased and inconsistent.
>
> http://www.soderbom.net/lecture15final.pdf
>
>
> Regards,
>
> Fernando Cunha
>
>
> -----Mensagem original-----
> De: [email protected]
> [mailto:[email protected]] Em nome de Jacobs, David
> Enviada em: sexta-feira, 23 de março de 2012 17:15
> Para: '[email protected]'
> Assunto: st: RE: panel tobit with fixed effects
>
> Probit provides one part of the Tobit estimator, but I don't think a
> fixed-effect version of probit is possible, although a colleague in
> economics once claimed this isn't so.
>
> In any case, just throwing in case dummies to get fixed-effects only works
> for least squares (and then the standard errors probably will be off a bit)
> and maybe some count models. It most certainly is not a good idea for a
> tobit model.
>
> Dave Jacobs
>
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of Fernando Cunha
> Sent: Friday, March 23, 2012 12:14 PM
> To: [email protected]
> Subject: st: panel tobit with fixed effects
>
> Dear Statalisters,
>
>
> I am trying to estimate a panel tobit model with fixed effects.
>
> I know that stata only estimate panel tobit model with random effects.
>
> I have a balanced panel.
>
> Can you help me?
>
> Regards
>
> Fernando Cunha
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
>
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/