Over identification & weak instrument tests in a 2SLS with more than one IV

[Zhihong Wang]

Dear All,
I have the following variables in a 2SLS model.

Ivregress 2slsl y (x1 x2 = z1 z2 z3) x3 x4 x5 i.fyear i.sic

I was trying to do a endogeneity test, an over identification test, and a weak instrument test by using the following commands:
Estat endogenous x1 x2
Estat overid
estat firststage x1 x2

I used these commands to run the test when I only have one IV in my model previously, but I am not sure if the way that I use the commands would be the same when I have two IVs.
If you know how to use these commands when there are more than one IV, could you please let me know if this is the right way to run the code? Thank you so much for your help.

[Fei Wang]

Yes, commands remain the same as you have multiple endogenous regressors under homoskedasticity. But -estat firststage- doesn't allow for varlist, so just run -estat firststage- after -ivregress 2sls-.

[Zhihong Wang]

Got it. Thank you so much, Fei!