Hello all,
After performing a perfectly balanced matching with 2:1 nearest neighbour and replacement we now want to run logistic regression and cox proportional hazard on those matched cases. We would like to adjust for the weights created by matchit (2:1 & replacement) and for the matching as well.
Clogit for example does not take into account the weights, but with strata for the pairing. After checking multiple packages and functions I wonder if there is a function that is taking care of both problems?
Any help and advice is highly appreciated!
Best regards,
Heiko Kaiser, MD, DESA
Division of Cardiothoracic Anesthesia
Washington University in St. Louis
Hello,
I would like to know the formula used to derive the weights that are
generated when using exact matching. I have not been able to find this in
any of the documentation or on the list-serv, and am hoping someone will be
able to provide it? Thanks very much.
Sincerely,
Deinera
