Sami Keskek wrote:
I would ask if any of you familiar with Bivariate (multi variate) Tobit.
I have the following problem:
I have a dependent variable, Y, censored from both below and above
and trying to estimate following regression:
Yt = a+ bYt-k + BX +u
is there anyone who knows how to do Bivariate Tobit in STATA.
ALSO, what else can be done in the case of heteroskedasticty ?
I want to add that above threshold is changing over time, (below is
constant).
--------------------------------------------------------------------------------
Not familiar with it, but if this is any help, a websearch brings up Daniel
Lawson's webpage ( http://users.drew.edu/dlawson/ ) where he's posted a
Stata do-file for bivariate tobit.
Also, take a look at -gllamm-.
I suspect that you will need something more like a bivariate analogue
of -cnreg- if your upper censoring values aren't fixed.
Joseph Coveney
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
