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: Cragg's Tobit


From   Andrea Rispoli <[email protected]>
To   [email protected]
Subject   st: Cragg's Tobit
Date   Wed, 4 Jul 2012 13:17:27 +0100

Dear Statalisters,
I am performing an analysis on panel data and my dependent variable is
continuous non negative, therefore I started by running a xttobit
model.
However I am now considering the possibility that the data generating
process is different when y=0 and when y>0. Therefore I was
considering using a craggit model where in the first stage I predict
the probability that y>0 and then, in the second stage, the actual
value of y.

In case you think that this is sensible, my question is how to reflect
the panel nature of the data in this case? I don't think craggit
allows it?

(The alternative I was thinking about is to use xtprobit to predict
y=0 vs y=1 ( if y>0), calculate the inv Mills Ratio and then use it as
a regressor in a xttobit. where I use all the values of y).

I am looking forward to receiving your valuable comments.
Thank you very much in advance!
Best Regards
AR
*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index