I have found Austin`s article
http://www.stata-journal.com/article.html?article=st0136 instructive for
such questions. Any endogenous regressors for which you do not provide an
instrument probably causes biases in your results.
Your second question is unclear. If you have a limited dependent variable,
you probably want to look at commands such as -h ivprobit-...
HTH
Martin
----- Original Message -----
From: "Carlos Rodriguez" <[email protected]>
To: <[email protected]>
Sent: Monday, December 29, 2008 6:32 PM
Subject: st: IV 2SLS regression
Hello list members,
I have a couple of questins regarding ivregress 2sls:
1) is it wrong to include some regressors which might be endogenous as
controls, in addition to the instrumented main endogenous explanatory
variable?
2) can one use a LDV in an ivregress 2sls model? does it cause bias?
thanks! happy holidays
*
* 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/
*
* 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/
