The DOI matches its Crossref record; 95 of the 95 references it cites were found in a registry or an index.
An Introduction to Propensity Score Methods for Reducing the Effects of Confounding in Observational Studies
Open accessAbstract
The propensity score is the probability of treatment assignment conditional on observed baseline characteristics. The propensity score allows one to design and analyze an observational (nonrandomized) study so that it mimics some of the particular characteristics of a randomized controlled trial. In particular, the propensity score is a balancing score: conditional on the propensity score, the distribution of observed baseline covariates will be similar between treated and untreated subjects. I describe 4 different propensity score methods: matching on the propensity score, stratification on the propensity score, inverse probability of treatment weighting using the propensity score, and covariate adjustment using the propensity score. I describe balance diagnostics for examining whether the propensity score model has been adequately specified. Furthermore, I discuss differences between regression-based methods and propensity score-based methods for the analysis of observational data. I describe different causal average treatment effects and their relationship with propensity score analyses.
Overview
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.
Integrity signals
Registry
Cites
Statistics
Verification
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.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The study maintained an active comparator, new-user design, with propensity score matching that adjusted for baseline use of other antidiabetic drugs to minimize confounding by cotreatment.39”
From Neurodegeneration and Stroke After Semaglutide and Tirzepatide in Patients With Diabetes and Obesity (2025) · cites this paper as [39]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The impact of this implementation was evaluated by comparing clinical outcomes before and after system deployment, using propensity score matching to account for potential confounding factors43.”
From Machine learning predicts sepsis deterioration trajectories. (2026) · cites this paper as [43]
The cited source says what the claim attributes to it.
In the citing paper
“PSM is considered a robust method (Austin, 2011; Benedetto et al., 2018).”
From Midwifery continuity of care, breastfeeding and neonatal hyperbilirubinemia: A retrospective cohort study (2024) · cites this paper as Austin, 2011
The cited source says what the claim attributes to it.
In the citing paper
“PSM is an analytic approach to reduce bias of measured confounding effects from covariates (Austin, 2011; Benedetto et al., 2018).”
From Midwifery continuity of care, breastfeeding and neonatal hyperbilirubinemia: A retrospective cohort study (2024) · cites this paper as Austin, 2011
In the citing paper
“All of these models, including more advanced techniques such as propensity scores [46] or inverse probability weighting, rely on the assumption of no unmeasured confounding for the validity of the effect estimate.”
From COSMOS-E: Guidance on conducting systematic reviews and meta-analyses of observational studies of etiology (2019) · cites this paper as [46]
In the citing paper
“Similarly, in cohort studies, vaccination against influenza not only protected against hospitalisation for pneumonia but also against hospitalisation for injury or trauma [46], indicating that the beneficial effect on pneumonia may have been overestimated.”
From COSMOS-E: Guidance on conducting systematic reviews and meta-analyses of observational studies of etiology (2019) · cites this paper as [46]
In the citing paper
“There are four principal ways to use the propensity score to obtain an estimated treatment effect: matching, stratification, inverse probability weighting, and covariate adjustment (7). Each method will adjust for differences in characteristics of the intervention and control groups and, in so doing, minimize the effects of confounding.”
From Natural Experiments: An Overview of Methods, Approaches, and Contributions to Public Health Intervention Research (2017) · cites this paper as [7]
In the citing paper
“This approach adjusted for confounding from all factors shared across individuals initiating analgesic treatment with opioids and with NSAIDs (eg, indications for pain treatment)”
From Association of opioid prescription initiation during adolescence and young adulthood with subsequent substance-related morbidity (2020) · cites this paper as [42]
In the citing paper
“The active comparator design cannot account for unmeasured factors that differentiate opioid and NSAID initiators”
From Association of opioid prescription initiation during adolescence and young adulthood with subsequent substance-related morbidity (2020) · cites this paper as [42]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The central role of the propensity score in observational studies for causal effects
ROSENBAUM, P. R., & RUBIN, D. B. (1983) · Biometrika · doi:10.1093/biomet/70.1.41 · Cited by 31,241
A simulation study of the number of events per variable in logistic regression analysis
Peduzzi, P., Concato, J., Kemper, E., Holford, T. R., & Feinstein, A. R. (1996) · Journal of Clinical Epidemiology · doi:10.1016/s0895-4356(96)00236-3 · Cited by 9,655
Estimating causal effects of treatments in randomized and nonrandomized studies
Rubin, D. B. (1974) · Journal of Educational Psychology · doi:10.1037/h0037350 · Cited by 9,436
Austin, P. C. (2009) · Statistics in Medicine · doi:10.1002/sim.3697 · Cited by 6,758
Self-citationRosenbaum, P. R., & Rubin, D. B. (1985) · The American Statistician · doi:10.2307/2683903 · Cited by 6,472
Marginal Structural Models and Causal Inference in Epidemiology
Robins, J. M., Hernán, M. Á., & Brumback, B. (2000) · Epidemiology · doi:10.1097/00001648-200009000-00011 · Cited by 5,581
MatchIt : Nonparametric Preprocessing for Parametric Causal Inference
Ho, D. E., Imai, K., King, G., & Stuart, E. A. (2011) · Journal of Statistical Software · doi:10.18637/jss.v042.i08 · Cited by 4,385
Matching as Nonparametric Preprocessing for Reducing Model Dependence in Parametric Causal Inference
Ho, D. E., Imai, K., King, G., & Stuart, E. A. (2007) · Political Analysis · doi:10.1093/pan/mpl013 · Cited by 4,285
Austin, P. C. (2011) · Pharmaceutical Statistics · doi:10.1002/pst.433 · Cited by 3,949
Self-citationCausal Diagrams for Epidemiologic Research
Greenland, S., Pearl, J., & Robins, J. M. (1999) · Epidemiology · doi:10.1097/00001648-199901000-00008 · Cited by 3,728
Cited by
Sorted by citations
Benchimol, E. I., Smeeth, L., Guttmann, A., Harron, K., Moher, D., Petersen, I., Sørensen, H. T., von Elm, E., Langan, S. M., & RECORD Working Committee (2015) · PLOS Medicine · doi:10.1371/journal.pmed.1001885 · Cited by 5,749
Austin, P. C., & Stuart, E. A. (2015) · Statistics in Medicine · doi:10.1002/sim.6607 · Cited by 4,495
Self-citationTaquet, M., Geddes, J. R., Husain, M., Luciano, S., & Harrison, P. J. (2021) · The Lancet Psychiatry · doi:10.1016/s2215-0366(21)00084-5 · Cited by 2,189
“HRs for COVID-19 diagnosis compared with the additional four index events showed more variation with time, partly reflecting the natural history of the comparator condition (appendix, pp 16–19, 36).”
Wang, X., & Cheng, Z. (2020) · CHEST · doi:10.1016/j.chest.2020.03.012 · Cited by 2,214
Taquet, M., Luciano, S., Geddes, J. R., & Harrison, P. J. (2021) · The Lancet Psychiatry · doi:10.1016/s2215-0366(20)30462-4 · Cited by 1,484
Metadata
- Authors
- Austin, P. C.
- Affiliations
- University of Toronto (CA)
- Corresponding author
- Austin, Peter C.
- ORCID
- Austin, Peter C.
- Venue
- Multivariate Behavioral Research
- Publisher
- Informa UK Limited
- Published
- 2011-05-31
- Volume
- 46
- Issue
- 3
- Pages
- 399-424
- ISSN
- 0027-3171 (ISSN-L)
- 1532-7906
- PMC
- PMC3144483
- OpenAlex
- W2036193982
- Cited by
- 12,242
- References
- 95
- Citations by year
- 2026: 1460 · 2025: 1302 · 2024: 1187 · 2023: 1145 · 2022: 1277 · 2021: 1253 · 2020: 1065 · 2019: 850 · 2018: 781 · 2017: 628 · 2016: 560 · 2015: 353 · 2014: 221 · 2013: 122 · 2012: 28
- FWCI
- 104.26
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- Multivariate Behavioral Research (publishedVersion)
- Europe PMC (PubMed Central) (publishedVersion)
- PubMed Central (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Institute for Clinical Evaluative Sciences
- Ontario Ministry of Health and Long-Term Care
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Keywords
- propensity score, confounding, observational studies, propensity score matching, stratification, inverse probability of treatment weighting, covariate adjustment, regression-based methods
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
