Dear Mike,
I wrote what I understand in
http://www.stata.com/statalist/archive/2004-09/msg00562.html
And I would be thrilled if more knowlegeable people were to add their voice.
Based on the explanation there, you *must* put x1 in the selection equation
too
heckman y x1, select (mover=x2 x1) twostep
gen stayer=1-mover
heckman y x1, select (stayer=x2 x1) twostep
Renzo
----------------------------------------------------------------------------
----
*From "Michael Johnson" <[email protected]>
To [email protected]
Subject st: switching regression model
Date Sun, 26 Sep 2004 19:26:48 -0500
----------------------------------------------------------------------------
----
Dear lister:
Do you think it is correct to do the switching model as follows (take
mover-stayer for example):
heckman y x1, select (mover=x2) twostep
gen stayer=1-mover
heckman y x1, select (stayer=x2) twostep
Thanks a lot
Mike
*
* 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/
