[Limdep Nlogit List] Imposing restrictions into a bivariate tobit model

[William Greene]

Bilgic.
The bivariate tobit model estimates gamma1 = beta1/sigma1 and
gamma2 = beta2/sigma2.  As such, it is not possible to impose
a cross equation restriction on the slope vectors - beta1(j) may
equal beta2(j), but even if so, gamma1(j) will not equal 
gamma2(j).  Alternatively, if you constrain equality across the
gamma vectors, which you can to in nlogit4, it will not impose
equality on the elements of beta because of the rescaling by 
sigma1 and sigma2.  NLOGIT 4 is the same as previous versions of
LIMDEP and NLOGIT.
/Bill Greene



----- Original Message -----
From: "Abdulbaki Bilgic" <tebrik at yahoo.com>
To: "Limdep and Nlogit Mailing List" <limdep at limdep.itls.usyd.edu.au>
Sent: Friday, July 4, 2008 3:23:55 AM (GMT-0500) America/New_York
Subject: [Limdep Nlogit List] Imposing restrictions into a bivariate tobit model

Dear All,
I would like to impose a cross equation restriction into a bivariate censored Tobit model. I know previous Limdep versions do not allow, but can i do it now in nlogit4? Your help would be greatly appreciated.
Best regards,

Bilgic


      
_______________________________________________
Limdep site list
Limdep at limdep.itls.usyd.edu.au
http://limdep.itls.usyd.edu.au


-- 
Professor William Greene
Department of Economics
Stern School of Business
New York University
44 West 4th St., Rm. 7-78
New York, NY   10012
http://www.stern.nyu.edu/~wgreene
212.998.0876