Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

st: Two stages ivprobit, robust standard errors in first stage


From   Laurie Molina <molinalaurie@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   st: Two stages ivprobit, robust standard errors in first stage
Date   Sat, 16 Feb 2013 23:38:11 -0600

Dear all,

I would appreciate if you can help me with two questions on ivprobit.

1. When using the command ivprobit with the twostage estimation
method, I notice that the resported standard errors for the first
stage estimation, correspond to the the non robust standard errors in
a simple ols regression. (I replicated the coefficient results
manually).
When looking at ivprobit options, I notice that vce(robust) is not available.
How can I make sure, that the estimation procedure in the second stage
will use the appropiate standard errors?

2. To replicate the second stage results, to my understanding the
appropiate procedure is to run a probit with the original explanatory
variable (endogenous) and the residuals of the first stage. With this
procedure I can replicate the ivprobit results for the exactly
identified case with only one instrument for the endogenous variable.
But for the case with two instruments for the endogenous variable, by
following this exact same procedure, I do not replicate stata ivprobit
results... Is there any difference in the procedure I should follow
for the overindentified case?

Thanks you very much in advance!

Laurie
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


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