Hi all,
I am using command psmatch2 to estimate ATT on my data.
but I want to get all TT(treatment effect on treated) and TU (treatment effect on untreated) after matched for the observations, instead of directly get ATT or ATU by using command display r(att).
and then I could use command sum TT or sum TU to get ATT(average treatment effect on treated) and ATU(average treatment effect on untreated).
well, I found following command by typing "help psmatch2":
> g att = .
> egen g = group(groupvars)
> levels g, local(gr)
> qui foreach j of local gr {
> psmatch2 treatvar varlist if g==`j', out(outvar)
> replace att = r(att) if g==`j' > }
> sum att
it seems this command can help me get the TT for all the observations, but I have no idea what the "groupvar" means.
and my command would be like "psmatch2 samplebnoro `exp', outcome(logall) n(1) ate ties logit common "
- samplenoro is treated variable
- `exp' is the local of covariates
hope someone can help me with this question.
thanks!
I am using command psmatch2 to estimate ATT on my data.
but I want to get all TT(treatment effect on treated) and TU (treatment effect on untreated) after matched for the observations, instead of directly get ATT or ATU by using command display r(att).
and then I could use command sum TT or sum TU to get ATT(average treatment effect on treated) and ATU(average treatment effect on untreated).
well, I found following command by typing "help psmatch2":
> g att = .
> egen g = group(groupvars)
> levels g, local(gr)
> qui foreach j of local gr {
> psmatch2 treatvar varlist if g==`j', out(outvar)
> replace att = r(att) if g==`j' > }
> sum att
it seems this command can help me get the TT for all the observations, but I have no idea what the "groupvar" means.
and my command would be like "psmatch2 samplebnoro `exp', outcome(logall) n(1) ate ties logit common "
- samplenoro is treated variable
- `exp' is the local of covariates
hope someone can help me with this question.
thanks!