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

st: question about ivprob


From   TAKESHI MIYATA <miyata.7@osu.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: question about ivprob
Date   Thu, 05 May 2005 13:50:01 -0400

Hello, I have two questions about the ivprob program. A previous question posted by Nick Cox wrote: 

with the following two equations: 
Eq2) A2 = A1 + A3 + A6 + A7 
Eq1) A1 = A2 + A3 + A4 + A5 
Variable A1 is dichotomous and A2 is continuous: 
Some of A3-A7 are dichotomous and some of A3-A7 are continuous. 
I have run the following STATA command to implement the IVPROB procedure: ivprob A1, endog(A2) iv(A6 A7)exog(A3 A4 A5). 

I have a very similar equation for which I am attempting to control for an endogenous variable. My questions are: 

1. A3 is used in both equations, and is exogenous to both. However based on this example, A3 is not identified any differently from the other exogenous variables such as A4 and A5 (which only enter equation 1). I would like to know if this is the correct way of specifying variables under this specific model. Based on the code above, it’s not clear to me how the distinction between A3 (which appears in both equations) vs. A4 and A5 (which only appear in equation 1) is made. 
2. I am also searching for ways to test existence of endogenous variables with a second-stage limited dependent variable model and first-stage continuous variable model. Can the standard Hausman test be used in this case to test for endogeneity or does it need to be modified in some way? If modification is necessary, do you have suggestions for references on how to modify the test or does code exist to run this test? 

I would greatly appreciate any comments or suggestions. I thank you for your time. 


*
*   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