Bookmark and Share

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]

st: Use ml to fit for simultaneous bivariate probit with partial observability


From   健 张 <victerzj2@yahoo.com.cn>
To   stata <statalist@hsphsun2.harvard.edu>
Subject   st: Use ml to fit for simultaneous bivariate probit with partial observability
Date   Fri, 23 Sep 2011 05:40:01 +0800 (CST)

Hi, all:
I am trying to write my ml code to fit for a simultaneous bivariate probit with partial observability case. It is similar to Feinstein (1990)'s DCE model.
Y1i=X1i*b+ui
Y2i=X2i*c+F(X1i*b)*d+vi
Although, stata has the predefined command, biprobit (...)(...), partial for the partial observability case, the help file of biprobit does not give an answer for how to code the simultaneous case with F(X1i*b) in the second equation. Therefore, I plan to write my own ml code to deal with the problem. So far, I have had the right likelihood evaluator and I know I should use the code similar to ml model lf bipp_lf (Y1i=X1i)(Y2i=X2i......)
However, I dont know how to include F(X1i*b), which is P(Y1i=1), into the second equation. sSince it is also a partial observability case and I only know the product of Y1i*Y2i, I can not simply put Y1i in the second equation.  
Any comment is welcomed. Thank you in advance!!
 
 
Best,
Jian 

*
*   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/


© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index