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: bivariate probit using -gllamm-
From
Dimitrije Tišma <[email protected]>
To
[email protected]
Subject
Re: st: bivariate probit using -gllamm-
Date
Thu, 4 Mar 2010 10:26:23 +0100
Well, I wanted more than just to reproduce -biprobit- results. If it
is possible to do joint estimations with -gllamm- I could (or, I
believe I could, please correct me if I am wrong) also get random
effects and their respective probabilities by using appropriate
-gllamm- options, such as ip(f). And this is, to best of my knowledge,
not possible with -biprobit- or -mvprobit-. Best,
Dimitrije
2010/3/3 Stas Kolenikov <[email protected]>:
> Why do you want to use -gllamm- for this? -biprobit- should be way faster.
> It is probably doable, but you would need to impose some odd constraints
> like unit loadings of the common latent variable in both equations.
>
> On Wed, Mar 3, 2010 at 10:18 AM, Dimitrije Tišma
> <[email protected]>wrote:
>
>> I was wondering if it is possible to do a bivariate probit regression
>> using -gllamm- rather than the built-in comman -biprobit-. If yes,
>> what would be the basic syntax? I have looked up everywhere (or at
>> least I think I did), -gllamm- manual included, but haven´t found a
>> lot on this. Thanks!
>>
>
> --
> Stas Kolenikov, also found at http://stas.kolenikov.name
> Small print: I use this email account for mailing lists only.
>
> *
> * 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/