PSM-psmatch2

[Dayla Spassio]

Hi all,
i have recently started reading and studying the matching procedure, i happened to see these two codes and i can't understand the difference. can anyone help me? thank you

psmatch2 treat x1 x3 , outcome(outcome_variable)  neighbor(1)

 probit treat x1 x2 predict ps, pr su ps if e(sample)  
* Matching by nearest neighbor
 psmatch2 treat, pscore(ps) neighbor(1) noreplacement

[Øyvind Snilsberg]

the difference is the noreplacement option, also the covariates differ but I guess that's a typo.

[Dayla Spassio]

Yes, it is a typo. Thank you very much. So I can decide whether to calculate the propensity score with probit or have the psmatch2 command do it all? thanks

[Øyvind Snilsberg]

yes. or you can use logit which is equivalent to psmatch2 with logit option.

[Dayla Spassio]

ok, thanks!!