Statalist The Stata Listserver


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

Re: st: IVtobit estimation


From   "Austin Nichols" <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: IVtobit estimation
Date   Tue, 17 Apr 2007 15:47:31 -0400

Leonor--
Richard makes an excellent point.  I also wonder if instead of -ivtobit- you
can use -qvf- (-findit qvf- to install).  I suspect many -tobit-
models that impose
censoring at zero in fact have a theoretically nonegative dep var, and no
censoring at all.

On 4/15/07, Richard Williams <Richard.A.Williams.5@nd.edu> wrote:
At 09:38 PM 4/14/2007, Leonor Saravia wrote:
>Hello Statalist,
>
>I'm using the ivtobit6 command to do my regressions in Stata 8, but
>when I run the complete model including the ll(0) (That's the
>censoring point the dependent variable has), Stata tells me that I
>can't use that extension, in fact, it tells: "invalid ll".  The model
>which i'm trying to run is:
>
>ivtobit6 inversion, endog(impprom) iv(imppromVI) exog(PIB98
>industria1-industria8 tamano1 tamano2 region2-region13),ll(0)
>
>When I run the same model without the ll(0), the command functions well.

It looks like you have an extra comma before ll(0).

However, why even use this in the first place?  The package
description says "Stata 8.2 or 9.x users should use official ivprobit
and ivtobit." Updating from Stata 8 to 8.2 is free.
*
*   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 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index