Table 2List of Matching Algorithms

MethodTypeDistanceCaliper, Y/NClusteringMatching ratio to control
VMVMLinear GPSYk-means1:1:1…1
VM2VMLinear GPSYk-means1:2:2…2
VMncVMLinear GPSNk-means1:1:1…1
VMnrVM without replacementLinear GPSYk-means1:1:1…1
VMFVMLinear GPSYFuzzy1:1:1…1
KMVM logit(r^(t,X), r^(t′,X)) Yk-means1:1:1…1
KMncVM logit(r^(t,X), r^(t′,X)) Nk-means1:1:1…1
FMVM logit(r^(t,X), r^(t′,X)) YFuzzy1:1:1…1
FMncVM logit(r^(t,X), r^(t′,X)) NFuzzy1:1:1…1
GPSBasicMahalanobis GPSYNone1:1:1…1
GPSncBasicMahalanobis GPSNNone1:1:1…1
COVncBasicMahalanobis covariatesNNone1:1:1…1

Abbreviations: COVnc, covariate matching, no caliper; FM, fuzzy clustering matching; FMnc, fuzzy clustering matching, no caliper; GPS, Mahalanobis on the generalized propensity score; GPSnc, Mahalanobis on the generalized propensity score, no caliper; KM, k-means matching; KMnc, k-means matching, no caliper; N, no; VM, vector matching; VM2, vector matching to 2 units in other groups; VMF, vector matching, fuzzy clustering; VMnc, vector matching, no caliper; VMnr, vector matching, no replacement; Y, yes.

From: Creating and Testing Methods to Estimate Treatment Effect in Observational Studies with Three or More Treatments

Cover of Creating and Testing Methods to Estimate Treatment Effect in Observational Studies with Three or More Treatments
Creating and Testing Methods to Estimate Treatment Effect in Observational Studies with Three or More Treatments [Internet].
Gutman R, Scotina A, Smith RJ, et al.
Copyright © 2020. Brown University. All Rights Reserved.

This book is distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License which permits noncommercial use and distribution provided the original author(s) and source are credited. (See https://creativecommons.org/licenses/by-nc-nd/4.0/

NCBI Bookshelf. A service of the National Library of Medicine, National Institutes of Health.