Marie, Martin, Partha,
M. G. Keshk wrote a program called cdsimeq
that will handle some forms of simultanous probit.
On the command line, type: findit cdsimeq
Cheers,
Robert
Robert A. Yaffee, Ph.D.
Research Professor
Silver School of Social Work
New York University
Biosketch: http://homepages.nyu.edu/~ray1/Biosketch2009.pdf
CV: http://homepages.nyu.edu/~ray1/vita.pdf
----- Original Message -----
From: Partha Deb <[email protected]>
Date: Thursday, October 8, 2009 9:42 am
Subject: Re: st: simultaneous probit model
To: [email protected]
> <>
> Notation is important here. The model you have written down is not
> quite model 6 in Maddala. Model 6 has
>
> (1) Y1* = a*Y2* + b*X1 + e1
> (2) Y2* = b*Y1* + c*X2 + e2
>
> i.e., the endogenous regressors on the RHS are the latent indices
> underlying Y1 and Y2, not the binary indicators themselves. If this
> is
> the model you want, Maddala, on the pages you've cited, outlines a
> 2-step plug in method. That's straightforward to implement. Standard
>
> errors are more complicated, but you could just bootstrap it all to
> get
> consistent standard errors.
>
> best.
>
> Partha
>
>
> Marie-Benoit MAGRINI wrote:
> > Hello,
> >
> > I am looking for a program allowing me to implement the « model 6 »
> in
> > the book of Maddala (1983, “Limited dependent and qualitative
> > variables in econometrics”, chapter 8 about the two-stage estimation
>
> > methods, page 246).
> >
> > That is, I am trying to estimate the following simultaneous probit
> > model :
> >
> > (1) Y1 = a*Y2 + b*X1 + e1
> >
> > (2) Y2 = b*Y1 + c*X2 + e2
> >
> > where Y1 and Y2 are two endogeneous binary variables; X1 and X2 are
>
> > two sets of exogenous variables of Y1 and Y2 respectively; e1 and e2
>
> > the error terms.
> >
> > Y1 and Y2 are endogenously determined by each other.
> >
> > I have looked at the ‘cdsimeq’ program but I understand that it
> > corresponds to the model where one dependent variable is continuous
>
> > and the other binary. So it cannot be used in my case.
> >
> > I have also looked at the ‘biprobit’ procedure but I understand that
>
> > it is adapted only for recursive model that is only one dependent
> > variable is an explicative of the other one (the model 6 I’ve been
> > trying to estimate is not recursive).
> >
> > Could someone tell me if this simultaneous probit model can be
> > estimated with STATA ?
> >
> > best regards,
> >
> > mb magrini
> >
> > using Stata 10
> >
> > --------------------------------------------------------------
> > Marie-Benoît MAGRINI
> > PhD in Economics
> > INRA - French National Institute for Agricultural Research
> > UMR1248 AGIR
> > BP 52627
> > 31326 Castanet Tolosan
> > FRANCE
> > Phone: 33 (0)5 61 28 54 22
> > Fax: 33 (0)5 61 73 20 77
> > email: [email protected]
> > http://www.toulouse.inra.fr/agir
> > http://www.international.inra.fr
> > ---------------------------------------------------------------
> >
> >
> >
> >
> >
> >
> >
> > *
> > * 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/
>
> --
> Partha Deb
> Professor of Economics
> Hunter College
> ph: (212) 772-5435
> fax: (212) 772-5398
> http://urban.hunter.cuny.edu/~deb/
>
> Emancipate yourselves from mental slavery
> None but ourselves can free our minds.
> - Bob Marley
>
>
> *
> * 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/
