Hello Everyone,
I am trying to generate a twoway kdensity plot after running pscore (which I prefer over psmatch2 since pscore provides more detail on balancing property) and nearest neighbour matching. I was hoping to follow the kdensity plots given in this earlier post: https://www.statalist.org/forums/for...score-matching. However psmatch2 has the advantage of providing IDs after match that pscore doesn't.
Currently, I am running the following code to get a kdensity graph before matching, but I am not sure how to proceed after matching.
twoway (kdensity pscore1 if treatment==1) (kdensity pscore1 if treatment ==0, lpattern(dash)), ///
legend( label( 1 "treated") label( 2 "control" ) ) xtitle("propensity score")
and then run the nearest neighbour match after which I am not certain how to plot the post match treatment and control variables. Thank you!
Lori
I am trying to generate a twoway kdensity plot after running pscore (which I prefer over psmatch2 since pscore provides more detail on balancing property) and nearest neighbour matching. I was hoping to follow the kdensity plots given in this earlier post: https://www.statalist.org/forums/for...score-matching. However psmatch2 has the advantage of providing IDs after match that pscore doesn't.
Currently, I am running the following code to get a kdensity graph before matching, but I am not sure how to proceed after matching.
twoway (kdensity pscore1 if treatment==1) (kdensity pscore1 if treatment ==0, lpattern(dash)), ///
legend( label( 1 "treated") label( 2 "control" ) ) xtitle("propensity score")
and then run the nearest neighbour match after which I am not certain how to plot the post match treatment and control variables. Thank you!
Lori
Comment