Bookmark and Share

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.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: marginal after biprobit


From   Ayman Farahat <ayman.farahat@yahoo.com>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   Re: st: marginal after biprobit
Date   Thu, 22 Nov 2012 12:26:22 -0800 (PST)

Thanks Dimitriy 
That was very helpful. 
I have a follow up question on how to interpret the correlation coefficient (artrho, or rho)

In case when i have :
 biprobit (isclosed = myfailpricerisk lreviewnumber) (isgroupon = mygrouponziprisk mygrouponpricerisk lbrate)
The correlation measure the degree of association between the un-observed factors in equation 1 (isclosed) and equation 2 (isgroupon)
so if i have a positive and significant correlation i can conclude that the unobserved share some common  determinants . 


In second case 
 biprobit (isclosed = myfailpricerisk lreviewnumber ISGROUPON) (ISGROUPON = mygrouponziprisk mygrouponpricerisk lbrate)
how do you interpret the correlation?
I have found that the correlation switch signs from first to second case?

Best
Ayman





----- Original Message -----
From: Dimitriy V. Masterov <dvmaster@gmail.com>
To: Statalist <statalist@hsphsun2.harvard.edu>
Cc: 
Sent: Wednesday, November 21, 2012 5:03 PM
Subject: Re: st: marginal after biprobit

Ayman,

biprobit is the right command. Austin Nichols has instructions on
calculating the AME here:
www.stata.com/meeting/chicago11/materials/chi11_nichols.pdf.

There are several ways of doing it, some are better than others, but
they tend to produce similar results.

DVM

On Wed, Nov 21, 2012 at 4:47 PM, Ayman Farahat <ayman.farahat@yahoo.com> wrote:
> Hello ;
> I am working on a problem where the dependent variable (iscloed)  is binary and one of the regressors (isgroupon) is binary and endogenous.
> Based on advice i got from the statalist, it was suggested to use a biprobit,
> I ended up using something of the form
>
> biprobit (isclosed = myfailpricerisk lreviewnumber isgroupon) (isgroupon = mygrouponziprisk mygrouponpricerisk lbrate)
>
>
> A couple of questions :
> 1)  Is the biprobit the correct command?
> 2) how do i get the marginal effect of "isgroupon" on "iscolosed" ?
> Thanks
> Ayman
>
> *
> *   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/
*
*   For searches and help try:
*  http://www.stata.com/help.cgi?searchhttp://www.stata.com/support/faqs/resources/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/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index