Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: heckman/dataset issue


From   "Bradley, Steven W" <swb@indiana.edu>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: heckman/dataset issue
Date   Sun, 25 Sep 2005 19:31:33 -0500

Dear Statalist:
 
I am trying to run a Heckman correction on a panel data set that has a significant amount of attrition in the data as there are numerous new firms that drop out during the 8 year time period.  When I run heckman, I notice that the number of unobserved to be used in heckman is much smaller (13) as shown below.
 

Heckman selection model                         Number of obs      =      7637
(regression model with sample selection)        Censored obs       =        13
                                                Uncensored obs     =      7624
                                                Wald chi2(6)       =    731.45
Log likelihood = -82337.21                      Prob > chi2        =    0.0000

My data set is such that when a firm drops out, there are no subsequent years entered for that firm.  Do I need to have a year for each firm even if they drop out and just enter zeros for the dependent and independent variables?
 
Is there a way to go through and add observations easily?
 
Thanks for any advice!
 
Steve

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index