Different results between ivreg2 and xtivreg2

[Li Han]

Hi, im trying to use instrumental regression with panel data.

At first, I use xtivreg2:
xtset firm year
xtivreg2 y x1 (x2 = a b), fe robust

Then, I try to replicate the results, with ivreg2
ivreg2 y x1 (x2 = a b) i.firm i.year, robust
ivreg2 y x1 (x2 = a b) i.year, cluster(firm) robust

But both results are different from xtivreg2, fe
3 results also have same number of observations, so no singleton is removed
May I ask which function xtivreg2, fe exactly runs?

[Andrew Musau]

See FAQ Advice #12 on the requirement to identify community contributed commands. Here ivreg2 and xtivreg2 are both from SSC.

But both results are different from xtivreg2, fe

Yes, you are estimating different models. One has year fixed effects while the other does not.

[Phil Bromiley]

You will help us help you by following the FAQ on asking questions – provide Stata code in code delimiters, readable Stata output, and sample data using dataex. It would be nice for example in this case to be able to replicate your results or at least see what they really are.

Regarding Andrew's helpful comments, let me just note that the fixed effects is controlling for the panel which is presented as the firm, not the year.

Being able to replicate your problem is essential. Trying out what I think you did, I got the same results with both estimators.

use https://www.stata-press.com/data/r16/nlswork, clear
xtset
keep in 1/5000
xtivreg ln_w age c.age#c.age not_smsa (tenure = union south), fe
ivregress 2sls ln_w  c.age#c.age  not_smsa i.idcode (tenure = union south), 
g agesq=age*age
xtivreg2 ln_w age age agesq not_smsa (tenure = union south), fe
xi  i.idcode
ivreg2  ln_w age agesq   not_smsa _I* (tenure = union south),