CoChat
Sign Up
Cited by 513Advanced Causal Inference TechniquesStatistical Methods in Clinical TrialsStatistical Methods in Epidemiology

Double-adjustment in propensity score matching analysis: choosing a threshold for considering residual imbalance

Open access
Nguyen, Tri-Long, Collins, Gary S., Spence, Jessica, Daurès, Jean-Pierre, Devereaux, P. J., Landais, Paul, Le Manach, Yannick·2017·BMC Medical Research Methodology
DOI 10.1186/s12874-017-0338-0PMC PMC5408373
Open this paper in CoChat — free accountOpen PDF

Abstract

BACKGROUND: Double-adjustment can be used to remove confounding if imbalance exists after propensity score (PS) matching. However, it is not always possible to include all covariates in adjustment. We aimed to find the optimal imbalance threshold for entering covariates into regression. METHODS: We conducted a series of Monte Carlo simulations on virtual populations of 5,000 subjects. We performed PS 1:1 nearest-neighbor matching on each sample. We calculated standardized mean differences across groups to detect any remaining imbalance in the matched samples. We examined 25 thresholds (from 0.01 to 0.25, stepwise 0.01) for considering residual imbalance. The treatment effect was estimated using logistic regression that contained only those covariates considered to be unbalanced by these thresholds. RESULTS: We showed that regression adjustment could dramatically remove residual confounding bias when it included all of the covariates with a standardized difference greater than 0.10. The additional benefit was negligible when we also adjusted for covariates with less imbalance. We found that the mean squared error of the estimates was minimized under the same conditions. CONCLUSION: If covariate balance is not achieved, we recommend reiterating PS modeling until standardized differences below 0.10 are achieved on most covariates. In case of remaining imbalance, a double adjustment might be worth considering.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1186/s12874-017-0338-0

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Residual imbalance was handled through double adjustment in the outcome analyses to achieve double robustness to potential model misspecification.

    “residual imbalance was handled through double adjustment in the outcome analyses to achieve double robustness to potential model misspecification.46,47”

    From Hysterectomy versus uterine preservation for pelvic organ prolapse surgery: a prospective cohort study (2025) · cites this paper as [47]

    The Methods (page not available in our copy) describe outcome regressions on unbalanced covariates after propensity-score matching and call the resulting estimator double-robust. The Results report reduced residual bias, but the Discussion calls double-adjustment model-dependent and reserves further misspecification scenarios for future study. The paper therefore supports using double adjustment for residual imbalance, not the claimed robustness to potential model misspecification. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 1

  1. [34]Ho DE Imai K King G Stuart EA Matching as nonparametric preprocessing for reducing model dependence in parametric causal inference Polit Anal 2007 15 199 236 10.1093/pan/mpl013 · DOI

Cited by

Sorted by citations

Related

Authors
Nguyen, T.-L., Collins, G. S., Spence, J., Daurès, J.-P., Devereaux, P. J., Landais, P., & Le Manach, Y.
Affiliations
  • Université de Montpellier (FR)
  • Population Health Research Institute (CA)
ORCID
Venue
BMC Medical Research Methodology
Publisher
Springer Science and Business Media LLC
Published
2017-04-28
Volume
17
Issue
1
Pages
78-78
ISSN
1471-2288 (ISSN-L)
DOI
10.1186/s12874-017-0338-0
PMC
PMC5408373
OpenAlex
W2609185034
Cited by
512
References
35
Citations by year
2026: 65 · 2025: 79 · 2024: 76 · 2023: 76 · 2022: 86 · 2021: 61 · 2020: 32 · 2019: 19 · 2018: 12 · 2017: 5
FWCI
12.93
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • BMC Medical Research Methodology (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • University of Birmingham Research Portal (University of Birmingham) (publishedVersion, other-oa)
  • HAL (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
None
Topics
  • Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
Keywords
propensity score matching, standardized mean difference, covariate balance, regression adjustment, confounding, nearest neighbor matching, treatment effect estimation, mean squared error
MeSH terms
Algorithms, Computer Simulation, Humans, Monte Carlo Method, Models, Statistical, Bias, Logistic Models, Propensity Score

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review