Suest for gmm?

[nazlikaramollaoglu]

Dear all,
I would like to test the coefficient estimates obtained from the same GMM model run on two different samples. Is there any way to do that?
Thank you!

[Andrew Musau]

The syntax of gmm allows you to include interactions, so you proceed in the same way as you would with other estimators.

[Phil Bromiley]

This is what I answered to someone with a similar issue using reghdfe (just to show how you can program it)
What you can do is:
g x21=X_2 if time==1
replace x21=0 if time==2
g x22=X_2 if time==2
replace x22=0 if time==1
*Do the same for Z


reghdfe y X_1( x21 x22= z1 z2) ,absorb(FE1 FE2) vce(cluster G)

[nazlikaramollaoglu]

Dear Phil,
Thank you! However, I did not understand clearly what we are doing here.

I assume that GMM asymptotically distributed as normal distribution and the two samples are independent.
Then I calculate the t values as
(c1-c2)/sqrt(s1^2+s2^2).
where c1 and c2 are the coefficients of exchange rate, while s1 and s2 are standard deviations.