Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.

# Re: st: constrained tobit regression?

 From Matthias Greiff To statalist@hsphsun2.harvard.edu Subject Re: st: constrained tobit regression? Date Mon, 4 Feb 2013 13:06:26 +0100

```Right Maarten, I should be more precise.
Without the comma: - tobit var1 var 2 var 3 var4..., ll(0) constraint(1) - gives the message "option constraint() not allowed, r(198)".
With the comma: - tobit var1 var 2 var 3 var4..., ll(0), constraint(1) - gives the message "invalid 'constraint', r(198)".
Best
Matthias

"Does not work" can mean a lot of things. It is much more informative
if you told us what Stata told you when you tried that command.

I can see one error though: -tobit var1 var 2 var 3 var4..., ll(0),
constraint(1)- should have been: -tobit var1 var 2 var 3 var4...,
ll(0) constraint(1)-, i.e. without the second comma. In a Stata
command the comma indicates "all that follows are options", so you do
not separate options with commas.

-- Maarten

On Fri, Feb 1, 2013 at 1:52 PM, Matthias Greiff
<Matthias.Greiff@wirtschaft.uni-giessen.de> wrote:
> Dear all,
>
> I'm trying to run a tobit regression with a constraint. The ususal way to run a tobit regression is:
>
> tobit var1 var 2 var 3 var4..., ll(0)
>
> Is there a way to run a tobit regression with a constraint? In particular, I intend to incorporate a linear constraint that requires that some of the coefficients sum up to zero, e.g.,
>
> constraint 1 var2 + var3 = 0
>
> The command
>
> tobit var1 var 2 var 3 var4..., ll(0), constraint(1)
>
> does not work.
>
> Best
>
> Matthias

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/
```