No, this would not be correct. Constraints must be
linear (not, e.g., inequalities); they refer to parameter
values, not data; and they cannot include -if- conditions.
Also, these constraints are inconsistent insofar as
(e.g.) something cannot be in (60,100) if it is equal to 3.
The latter problem may reflect a typo.
That said, I regret that I do not understand what you
want here.
Nick
[email protected]
Mentzakis, Emmanouil
> Thank you very much. What I meant in my question was, if
> there is a way
> to relax the parallel line assumption when using intreval
> regression and
> I think what you prospose does exactly that.
>
> However, I d like to ask how could I specify these inetrvals?
>
> If I had these inetervals: 0-20, 21-60 and 61-100
>
> Would it be correct to write:
>
> constraint 1 depvar>0 & depvar<20 if depvar==1
> constraint 2 depvar>20 & depvar<60 if depvar==2
> constraint 3 depvar>60 & depvar<100 if depvar==3
>
> And then
>
> oglogit2 depvar indepvar, npl() constraints(1-3)
Richard Williams
> At 10:53 AM 12/1/2006, Mentzakis, Emmanouil wrote:
>
> >Dear all,
> >
> >I would like to estimate a generalised interval regression model.
> >
> >I know there is the option of goprobit but I would like to use the
> >interval information that I have.
> >
> >Does anybody know if it is possible?
> >
> >Best regards
> >Manos
>
> Manos, I'm not sure what a generalized interval regression model would
> be. Are there articles on it?
>
> Perhaps the idea would be that you could specify what the
> cutpoints were
> instead of having to estimate them? If so, maybe it could be
> done using
> the constraints option of gologit2 or goprobit.
*
* 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/
