st: re: how to implement this test?

[Kit Baum <kitbaum@mac.com>]

< >
Carola said

I need to run a test to find out how sensitive my estimates are to  
violations of the exclusion restriction of the instrumental variable I  
am using.  Could anyone let me know what the code is in STATA10?


If you mean testing whether it is valid to treat a particular variable  
as excluded from the equation (serving as an excluded instrument),  
merely change its status to included. Under the null hypothesis that  
it does not have a direct impact on the dependent variable, its  
coefficient should not be distinguishable from zero. Inclusion of  
irrelevant explanatory variables does not bias the point estimates of  
other variables, so if the variable plays no direct role in the  
equation, your estimates will not be sensitive to its use as an  
included exogenous variable. On the other hand, if it is significant  
when included, it causes bias and inconsistency to exclude it...

Kit Baum, Boston College Economics and DIW Berlin
http://ideas.repec.org/e/pba1.html
An Introduction to Modern Econometrics Using Stata:
http://www.stata-press.com/books/imeus.html


*
*   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/