An overview of propensity score matching methods for clustered data
Statistical Methods in Medical Research · 2023-04 · 32 (4) · 641-655
DOI: 10.1177/09622802221133556 ↗Kurz gefasst
Fachartikel in der Zeitschrift Statistical Methods in Medical Research, online erschienen am 25.11.2022. Verfasst von Benjamin Langworthy und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA. Hauptthemen laut MEDLINE: Aspirin. Die Arbeit wurde bisher 55-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIDCD NIH HHS, NCI NIH HHS, NHLBI NIH HHS.
Abstract (Originalsprache)
Propensity score matching is commonly used in observational studies to control for confounding and estimate the causal effects of a treatment or exposure. Frequently, in observational studies data are clustered, which adds to the complexity of using propensity score techniques. In this article, we give an overview of propensity score matching methods for clustered data, and highlight how propensity score matching can be used to account for not just measured confounders, but also unmeasured cluster level confounders. We also consider using machine learning methods such as generalized boosted models to estimate the propensity score and show that accounting for clustering when using these methods can greatly reduce the performance, particularly when there are a large number of clusters and a small number of subjects per cluster. In order to get around this we highlight scenarios where it may be possible to control for measured covariates using propensity score matching, while using fixed effects regression in the outcome model to control for cluster level covariates. Using simulation studies we compare the performance of different propensity score matching methods for clustered data across a number of different settings. Finally, as an illustrative example we apply propensity score matching methods for clustered data to study the causal effect of aspirin on hearing deterioration using data from the conservation of hearing study.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Biostatistics, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
- Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston, MA, USA.
ORCID-Profile: Benjamin Langworthy, Molin Wang
Förderung
- NIDCD NIH HHS
- NCI NIH HHS
- NHLBI NIH HHS
- National Institutes of Health
Zitieren
APA
Langworthy, B., Wu, Y., & Wang, M. (2023). An overview of propensity score matching methods for clustered data. Statistical Methods in Medical Research, 32(4), 641-655. https://doi.org/10.1177/09622802221133556
Vancouver
Langworthy B, Wu Y, Wang M. An overview of propensity score matching methods for clustered data. Statistical Methods in Medical Research. 2023;32(4):641-655. doi:10.1177/09622802221133556
BibTeX
@article{Langworthy2023,
author = {Langworthy, Benjamin and Wu, Yujie and Wang, Molin},
title = {An overview of propensity score matching methods for clustered data},
journal = {Statistical Methods in Medical Research},
year = {2023},
volume = {32},
number = {4},
pages = {641--655},
doi = {10.1177/09622802221133556}
}
EUVIMED