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: problem in biprobit with partial observability
From
健 张 <[email protected]>
To
[email protected]
Subject
st: problem in biprobit with partial observability
Date
Sat, 2 Apr 2011 23:59:13 +0800 (CST)
Hi, statalisters,
I am encountering a problem in writing the code of biprobit with partial observability. I have 402 firms, in which 268 firms are labelled as 0 and the rest are labelled as 1. So I define those 0 and 1 as my dependent variable y. Y is equal to y1 * y2. Those y1 and y2 are two latent variable and I dont observe y1 and y2. However, I am interested in y1 and y2. That is why I decide to use biprobit with partial observability. I found the code from http://www.stata.com/support/faqs/stat/biprobit.html. And that thread also describle very similar problem with mine. However, when I run the code provided in that thread, (generate y2 = y
biprobit (y x1 x2 x3)(y2 x1 x2 x4), partial ) stata report a error notice. It says "y is never 0". I interpret this notice as stata thinks all my obvervation in y is 1. But I did have observation with 0 in y. So I am really confused. Does any one know what happened in stata?
Thanks in advance!
*
* 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/