Dear Statalist
I have estimated an average treatment effect (ATE) on a binary outcome using tseffects nnmatch with the following specification:
teffects nnmatch (y x1 x2 x3 x4 x5) (treat), biasadj(x1 x2 x3 x4) ematch(x5) ate vce(robust)
I have a positive and significant ATE for treat==1.
I was wondering if it is possible to generate a figure based on this ATE calculation that shows the effect of the treatment on the outcome for my matched sample.
I.e. something like: the effect of treat==1 vs treat==0 on the change in odds of y==1 with 95% confidence intervals?
Any input on this problem would be greatly appreciated.
Sincerely,
Erik Aadland.
I have estimated an average treatment effect (ATE) on a binary outcome using tseffects nnmatch with the following specification:
teffects nnmatch (y x1 x2 x3 x4 x5) (treat), biasadj(x1 x2 x3 x4) ematch(x5) ate vce(robust)
I have a positive and significant ATE for treat==1.
I was wondering if it is possible to generate a figure based on this ATE calculation that shows the effect of the treatment on the outcome for my matched sample.
I.e. something like: the effect of treat==1 vs treat==0 on the change in odds of y==1 with 95% confidence intervals?
Any input on this problem would be greatly appreciated.
Sincerely,
Erik Aadland.
