Standard

A Fast Algorithm for Maximal Propensity Score Matching. / Ruzankin, Pavel S.

In: Methodology and Computing in Applied Probability, Vol. 22, No. 2, 01.06.2020, p. 477-495.

Research output: Contribution to journal › Article › peer-review

Harvard

Ruzankin, PS 2020, 'A Fast Algorithm for Maximal Propensity Score Matching', Methodology and Computing in Applied Probability, vol. 22, no. 2, pp. 477-495. https://doi.org/10.1007/s11009-019-09718-4

APA

Ruzankin, P. S. (2020). A Fast Algorithm for Maximal Propensity Score Matching. Methodology and Computing in Applied Probability, 22(2), 477-495. https://doi.org/10.1007/s11009-019-09718-4

Vancouver

Ruzankin PS. A Fast Algorithm for Maximal Propensity Score Matching. Methodology and Computing in Applied Probability. 2020 Jun 1;22(2):477-495. doi: 10.1007/s11009-019-09718-4

Author

Ruzankin, Pavel S. / A Fast Algorithm for Maximal Propensity Score Matching. In: Methodology and Computing in Applied Probability. 2020 ; Vol. 22, No. 2. pp. 477-495.

BibTeX

@article{a44dfcdec4ac41fc8279f3b8fe20dc0a,
title = "A Fast Algorithm for Maximal Propensity Score Matching",
abstract = "We present a new algorithm which detects the maximal possible number of matched disjoint pairs satisfying a given caliper when a bipartite matching is done with respect to a scalar index (e.g., propensity score), and constructs a corresponding matching. Variable width calipers are compatible with the technique, provided that the width of the caliper is a Lipschitz function of the index. If the observations are ordered with respect to the index then the matching needs O(N) operations, where N is the total number of subjects to be matched. The case of 1-to-n matching is also considered. We offer also a new fast algorithm for optimal complete one-to-one matching on a scalar index when the treatment and control groups are of the same size. This allows us to improve greedy nearest neighbor matching on a scalar index.",
keywords = "Matching with caliper, Nearest neighbor matching, Propensity score matching, Variable width caliper",
author = "Ruzankin, {Pavel S.}",
year = "2020",
month = jun,
day = "1",
doi = "10.1007/s11009-019-09718-4",
language = "English",
volume = "22",
pages = "477--495",
journal = "Methodology and Computing in Applied Probability",
issn = "1387-5841",
publisher = "Springer Netherlands",
number = "2",

}

RIS

TY - JOUR

T1 - A Fast Algorithm for Maximal Propensity Score Matching

AU - Ruzankin, Pavel S.

PY - 2020/6/1

Y1 - 2020/6/1

N2 - We present a new algorithm which detects the maximal possible number of matched disjoint pairs satisfying a given caliper when a bipartite matching is done with respect to a scalar index (e.g., propensity score), and constructs a corresponding matching. Variable width calipers are compatible with the technique, provided that the width of the caliper is a Lipschitz function of the index. If the observations are ordered with respect to the index then the matching needs O(N) operations, where N is the total number of subjects to be matched. The case of 1-to-n matching is also considered. We offer also a new fast algorithm for optimal complete one-to-one matching on a scalar index when the treatment and control groups are of the same size. This allows us to improve greedy nearest neighbor matching on a scalar index.

AB - We present a new algorithm which detects the maximal possible number of matched disjoint pairs satisfying a given caliper when a bipartite matching is done with respect to a scalar index (e.g., propensity score), and constructs a corresponding matching. Variable width calipers are compatible with the technique, provided that the width of the caliper is a Lipschitz function of the index. If the observations are ordered with respect to the index then the matching needs O(N) operations, where N is the total number of subjects to be matched. The case of 1-to-n matching is also considered. We offer also a new fast algorithm for optimal complete one-to-one matching on a scalar index when the treatment and control groups are of the same size. This allows us to improve greedy nearest neighbor matching on a scalar index.

KW - Matching with caliper

KW - Nearest neighbor matching

KW - Propensity score matching

KW - Variable width caliper

UR - http://www.scopus.com/inward/record.url?scp=85065409001&partnerID=8YFLogxK

U2 - 10.1007/s11009-019-09718-4

DO - 10.1007/s11009-019-09718-4

M3 - Article

AN - SCOPUS:85065409001

VL - 22

SP - 477

EP - 495

JO - Methodology and Computing in Applied Probability

JF - Methodology and Computing in Applied Probability

SN - 1387-5841

IS - 2

ER -

ID: 20047094