How to use MatchIT R package to use caliper width on logit of the propensity score instead of the propensity score?

Question

The R package MatchIT uses a caliper width on the standard deviation of the propensity score. Is there a way to use logit of the propensity score?

Answer 1

Yes. In the link argument, specifiy link = "linear.logit". Below is an example:

m <- matchit(A ~ X1 + X2, data = data, method = "nearest",
             distance = "glm", link = "linear.logit",
             caliper = .2)

This does nearest neighbor matching on the logit of the propensity score with a caliper of .2 standard deviations of the logit of the propensity score.