Supplementary Figures.pdf (698.38 kB)
Download file

Supplementary Figures E1-E3. Propensity score matching versus coarsened exact matching in observational comparative effectiveness research

Download (698.38 kB)
dataset
posted on 01.06.2021, 14:56 by David Guy, Igor Karp, Piotr Wilk, Joseph Chin, George Rodrigues
• Supplementary materials – figures:
o Figure E1a. Selection process for comparison one
o Figure E1b. Selection process for comparison two
o Figure E2a. Distribution of baseline covariates by PSM caliper width for comparison one
o Figure E2b. Distribution of baseline covariates by PSM caliper width for comparison two
o Figure E3a. Distribution of baseline covariates by CEM strategy for comparison one
o Figure E3b. Distribution of baseline covariates by CEM strategy for comparison two

Supplementary materials – figures
Figure E1a. Selection process for comparison one
Figure E1b. Selection process for comparison two
Figure E2a. Distribution of baseline covariates by PSM caliper width for comparison one
Figure E2b. Distribution of baseline covariates by PSM caliper width for comparison two
Figure E3a. Distribution of baseline covariates by CEM strategy for comparison one
Figure E3b. Distribution of baseline covariates by CEM strategy for comparison two

Supplementary materials – tables
Table E1a. Characteristics of PSM strategies for comparison one
Table E1b. Characteristics of PSM strategies for comparison two
Table E2a. Coarsening of covariates used in CEM for comparison one
Table E2b. Coarsening of covariates used in CEM for comparison two
Table E3a. Characteristics of CEM strategies for comparison one
Table E3b. Characteristics of CEM strategies for comparison two

Abstract
Aims & Methods: We compared propensity score matching (PSM) and coarsened exact matching (CEM) in balancing baseline characteristics between treatment groups using observational data obtained from a pan-Canadian prostate cancer radiotherapy database. Changes in effect estimates were evaluated as a function of improvements in balance, using results from RCTs to guide interpretation. Results: CEM and PSM improved balance between groups in both comparisons, while retaining the majority of original data. Improvements in balance were associated with effect estimates closer to those obtained in RCTs. Conclusions: CEM and PSM led to substantial improvements in balance between comparison groups, while retaining a considerable proportion of original data. This could lead to improved accuracy in effect estimates obtained using observational data in a variety of clinical situations.

Funding

The Physicians’ Service Inc. Foundation and the Ontario Graduate Scholarship program supported research training for David Guy.

History