Hi:
Can anyone help me on the following questions on 2SLS?
1) How to construct an appropriate instrument for an endogenous
variable? One suggestion is running gen varlag=var[_n-1]. Do I have to
use this procedure for all endogenous variables? Or, there are some
other better alternatives?
2) Can the predicted values for endogenous variables (saving predicted
values while the independent variables are regressed on them)work as
instruments?
3) How to construct instruments for endogenous variables that are
related to each other in a non-recursive way?
Thanks in advance for your kind feedbacks. Please do not forget that I
am almost a new learner on the topic. It is better for me if you kindly
explain the steps.
Shyamal
*
* 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/
