this depends on the method you use. For Mahalanobis, you can rescale your
variables. With CEM, you can choose different coarsenings.
Gary
--
*Gary King* - Albert J. Weatherhead III University Professor - Director,
IQSS <http://iq.harvard.edu/>- Harvard University
GaryKing.org - King(a)Harvard.edu - @KingGary <https://twitter.com/kinggary> -
617-500-7570 - fax 812-8581 - Assistant <king-assist(a)iq.harvard.edu>du>:
495-9271
On Wed, Jan 14, 2015 at 7:26 PM, Jay <jayodita(a)grandroundshealth.com> wrote:
Hi!
I have a question about weighing the
covariants that matchit uses for matching.
I have some covariants that are higher
priority to match on, and others that
I'd like to consider in the match given a
strong match on the first set.
Is there a way to include a weight vector
on the set of covariates?
Example:
Covariates = [age, comorbidity, gender,
back problem type 1, back problem type 2]
Weights = [1, 1, 1, 0.25, 0.25]
The resulting matches will be biased
towards minimizing the distance between
age, comorbidity, and gender to a greater
extent than minimizing the distance
between the back problems.
Thank you!
-
---
MatchIt mailing list served by HUIT
List Address: matchit(a)lists.gking.harvard.edu
Subscribe/Unsubscribe:
http://lists.gking.harvard.edu/mailman/listinfo/ei
MatchIt Software and Documentation:
http://gking.harvard.edu/matchit/
Browse/Search List Archive:
http://lists.gking.harvard.edu/mailman/private/matchit/
Matchit mailing list
Matchit(a)lists.gking.harvard.edu
To unsubscribe from this list or get other information:
https://lists.gking.harvard.edu/mailman/listinfo/matchit