Psmatch2

[Menal khan]

Hello everyone,
I am facing some problems in understanding which Stata command is best to estimate psm. firstly i applied following command which gives insignificant results

psmatch2 $treatment , outcome( $ylist ) pscore( myscore) neighbor(1)
----------------------------------------------------------------------------------------
        Variable     Sample |    Treated     Controls   Difference         S.E.   T-stat
----------------------------+-----------------------------------------------------------
       cd  Unmatched | .559554635   .537822731   .021731904   .008802807     2.47
                        ATT | .559554635   .520714656   .038839979   .043125644     0.90
----------------------------+-----------------------------------------------------------
Note: S.E. does not take into account that the propensity score is estimated.

then i applied psmatch2 command with calliper and the att is significant

 psmatch2 $treatment , outcome( $ylist ) pscore(myscore) radius caliper(0.03)
----------------------------------------------------------------------------------------
        Variable     Sample |    Treated     Controls   Difference         S.E.   T-stat
----------------------------+-----------------------------------------------------------
       cd  Unmatched | .559554635   .537822731   .021731904   .008802807     2.47
                        ATT | .559554635   .537381014   .022173621   .008812524     2.52
----------------------------+-----------------------------------------------------------
Note: S.E. does not take into account that the propensity score is estimated.

similarly teeffects also shows significant values

teffects psmatch ( $ylist  ) ( $treatment $xlist , logit), atet

Treatment-effects estimation                   Number of obs      =     22,647
Estimator      : propensity-score matching     Matches: requested =          1
Outcome model  : matching                                     min =          1
Treatment model: logit                                        max =        275
------------------------------------------------------------------------------
             |              AI Robust
   cd |      Coef.   Std. Err.      z    P>|z|     [95% Conf. Interval]
-------------+----------------------------------------------------------------
ATET         |
   treatment |
   (1 vs 0)  |   .0157403   .0057419     2.74   0.006     .0044865    .0269942
------------------------------------------------------------------------------

Here my question is which psmatch2 command should be preffered?
David Radwin