r - Should I put outcome variable in Matchit::matchit ()

Question

I would like to perform a logistic regression by adjusting for propensity score. My question is, do I have to include the outcome (binary in my case) in the propensity score calculation? Otherwise how else can I link the outcome variable to the matched data created?

library(MatchIt)
m.out<-matchit(treatment~var1+var2+var3+var4+outcome, data = data,method = "nearest", ratio=1)
dataMatched = match.data(m.out)
library(Zelig)
z.out = zelig(outcome ~ var1+var2+var3+var4, model = "logit",data = dataMatched )

Answer 1

The propensity score is stored as the variable distance in dataMatched, so you can include that as a covariate in your outcome regression just like any other covariate. That said, you don't need to do this. Matching on the propensity score already uses the propensity score to adjust for imbalance, so you don't need to use it again in the outcome regression model, especially if you're including covariates. It probably will not hurt, though.