Hi statistical experts,
look forward to your guidance on a question about PSM.
If i have 2 different outcomes (A) and (B) in the same study cohort, do I have to do separate matching process for each outcome? My ultimate goal is to conduct a cox regression analysing the association between outcome A or B and treatment using the matched cohort.
psmatch2 treatment $covariate, outcome(A) caliper (0.02) ate logit common
psmatch2 treatment $covariate, outcome(B) caliper (0.02) ate logit common
I run the above codes, and the number of cases and controls are slightly different in the two matched cohorts.
Did I do the matching correctly? or i should do a single matching using codes: psmatch2 treatment $covariate, caliper (0.02) ate logit common -- which did not specify the outcome.
can anyone give me some guidance which method is correct?
Thank you so much
look forward to your guidance on a question about PSM.
If i have 2 different outcomes (A) and (B) in the same study cohort, do I have to do separate matching process for each outcome? My ultimate goal is to conduct a cox regression analysing the association between outcome A or B and treatment using the matched cohort.
psmatch2 treatment $covariate, outcome(A) caliper (0.02) ate logit common
psmatch2 treatment $covariate, outcome(B) caliper (0.02) ate logit common
I run the above codes, and the number of cases and controls are slightly different in the two matched cohorts.
Did I do the matching correctly? or i should do a single matching using codes: psmatch2 treatment $covariate, caliper (0.02) ate logit common -- which did not specify the outcome.
can anyone give me some guidance which method is correct?
Thank you so much
