st: Re: IV tests in Stata

classic Classic list List threaded Threaded
1 message Options
Reply | Threaded
Open this post in threaded view

st: Re: IV tests in Stata

Christopher F Baum
< >
I think there are two things being confused here. A test of the  
hypothesis that the excluded instruments are orthogonal to the error  
process, commonly known as a test of overidentification or  
overidentifying restrictions, can only be done when your IV  
specification is overidentified (when you have more excluded  
instruments than included endogenous variables). You cannot challenge  
the instruments in an exactly identified specification.

On the other hand that orthogonality hypothesis is only one of three  
which should be tested for a given instrument. The other two are:

1) meaningful correlation between instrument(s) and endogenous  
variables: the various 'weak instruments' tests

2) the exclusion restriction: the instrument does not itself belong in  
the equation. Now if it does, it might be either exogenous or  
endogenous. Naturally, if it is excluded, it will be correlated with  
the error process, and will likely trigger rejection of the first  
hypothesis. That can readily be tested by including it in the  
equation. If you only have one instrument, you will have to find  
something else to identify the equation, but you do want to ensure  
that the hypothesis that the instrument has only an indirect effect on  
y (through the endogenous variable(s)) rather than a direct effect on  
y is reasonable for your instrument(s).

PS> Stata, unlike SAS, TSP, RATS, MATLAB, SPSS etc. is not an acronym.

Kit Baum, Boston College Economics and DIW Berlin
An Introduction to Modern Econometrics Using Stata:

On Dec 6, 2008, at 02:33 , Carlos wrote:

> Do all the parametric tests of sensitivity of IVs to the violation of
> the exclusion restriction that are available in STATA require more
> than one IV (=overidentification tests)?  In other words, what if I
> have only one IV?  Is ti possible to run such a sensitivity test in

*   For searches and help try: