Is xi: xtivreg the same as xi: ivregress 2sls

[rohan vaithilingam]

I want to check if my instrument variable is a weak instrument, in order to do so I have to perform an F test.
Here I have ran the regression with xi: xtivreg wage race age married (education = parents education), fe first


My problem is that I want to have the estat firststage, to check if the instrument is weak. This is not possible with xtivreg, this estat firststage I can only get with using
xi: ivregress 2sls wage race age married (education = parents education)

Now the problem is that the coefficients for xi: ivregress 2sls and xi: xtivreg is different. I can conclude for the estat firststage that the instrument is not weak.
But how can I else test if the instrument is weak or not for the xtivreg , I have to stick with the xtivreg model.

[Phil Bromiley]

Welcome to Statalist. You'll increase your chances of a useful answer by following the FAQ on asking questions - provide Stata code in code delimiters, readable Stat output, and sample data using dataex.

I don't see why you would want xi at all. xi is seldom needed in recent versions of Stata. What xi does in older versions is make numerical (0,1,2,) variables identified as i.x into dummies. This is totally different than an xt estimator.