Did2s R-square

[marilyn ibarra-caton]

The general did2s command goes not report R-square, how do I get it?

[FernandoRios]

You an estimate the "first - stage" of the model itself. And get it from there.
F

[Cat Santos]

Dear @FernandoRios,

Thank you for this helpful tip.

Does it mean that to calculate the R2 using did2s I simply can turn:

did2s output if subsample==1 [aw=_weights], first_stage(i.country_id i.year ///
control1 control2 control3 control4 control5) ///
second_stage(treat) treatment(treat) cluster(country_id)

Into:

reghdfe output  ///
control1 control2 control3 control4 control5 ///
i.country_id i.year if subsample==1 [aw=_weights], vce(cluster country_id)

And the R squared of the redhdfe will be the same R2 of the first did2s?

Am I calculating the first stage correctly?

Alternatively, could I use something like?

*predict outputp if e(sample) 
*corr output outputp if e(sample) 
*di r(rho)^2

The value I get using the reghdfe and corr is different though...

Thank you so much!

Best,
Cat