Addressing Extreme Propensity Scores via the Overlap Weights
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
The popular inverse probability weighting method in causal inference is often hampered by extreme propensity scores, resulting in biased estimates and excessive variance. A common remedy is to trim patients with extreme scores (i.e., remove them from the weighted analysis). However, such methods are often sensitive to the choice of cutoff points and discard a large proportion of the sample. The implications for bias and the precision of the treatment effect estimate are unclear. These problems are mitigated by a newly developed method, the overlap weighting method. Overlap weights emphasize the target population with the most overlap in observed characteristics between treatments, by continuously down-weighting the units in the tails of the propensity score distribution. Here we use simulations to compare overlap weights to standard inverse probability weighting with trimming, in terms of bias, variance, and 95% confidence interval coverage. A range of propensity score distributions are considered, including settings with substantial nonoverlap and extreme values. To facilitate practical implementation, we further provide a consistent estimator for the standard error of the treatment effect estimated using overlap weighting.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Overlap weighting emphasizes patients for whom either strategy was clinically plausible and limits the influence of extreme weights (17, 18).”
From Day-4 antipseudomonal and anti-MRSA de-escalation was not associated with higher mortality in critically ill patients with sepsis (2026) · cites this paper as [17]
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
Matching Methods for Causal Inference: A Review and a Look Forward
Stuart, E. A. (2010) · Statistical Science · doi:10.1214/09-sts313 · Cited by 5,478
Austin, P. C., & Stuart, E. A. (2015) · Statistics in Medicine · doi:10.1002/sim.6607 · Cited by 4,495
Constructing Inverse Probability Weights for Marginal Structural Models
Cole, S. R., & Hernan, M. A. (2008) · American Journal of Epidemiology · doi:10.1093/aje/kwn164 · Cited by 2,796
Lunceford, J. K., & Davidian, M. (2004) · Statistics in Medicine · doi:10.1002/sim.1903 · Cited by 1,674
Hirano, K., & Imbens, G. W. (2001) · Health Services and Outcomes Research Methodology · doi:10.1023/a:1020371312283 · Cited by 1,039
Dealing with limited overlap in estimation of average treatment effects
Crump, R. K., Hotz, V. J., Imbens, G. W., & Mitnik, O. A. (2009) · Biometrika · doi:10.1093/biomet/asn055 · Cited by 1,007
Balancing Covariates via Propensity Score Weighting
Li, F., Morgan, K. L., & Zaslavsky, A. M. (2018) · Journal of the American Statistical Association · doi:10.1080/01621459.2016.1260466 · Cited by 962
Self-citationRothman, K. J. (1988) · Cited by 690
Weight Trimming and Propensity Score Weighting
Lee, B. K., Lessler, J., & Stuart, E. A. (2011) · PLoS ONE · doi:10.1371/journal.pone.0018174 · Cited by 500
Cited by
Items 701–800 of 1,000
Observational studies: a perpetual quest for a signal among the noise
Gonzalez-Valencia, N. (2022) · Canadian Journal of Anesthesia/Journal canadien d anesthésie · doi:10.1007/s12630-022-02196-2
“it would be sensitive to the cut-off chosen for the purpose, at the cost of decreasing the representative sample.(10)”
BackgroundDelépine, T., Philippe, P., Cailliau, É., Houvenagel, É., Pascart, T., Deprez, X., Flipo, R., & Letarouilly, J.-G. (2022) · Revue du Rhumatisme · doi:10.1016/j.rhum.2022.09.004
Otaka, S., Ohbe, H., Igeta, R., Chiba, T., Ikeda, S., & Shiga, T. (2022) · Cardiology and Cardiovascular Medicine · doi:10.26502/fccm.92920279
“To confirm the robustness of our results, we performed a sensitivity analysis using overlap weights to balance the patients’ backgrounds between the groups [19-21].”
MethodKarapakula, G. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4324986
Evaluating propensity score weighting methods in heterogeneous population: a comparative studyPreprint
Hu, Y., Huang, C., Wang, C., Liu, Y., Yu, Y., & Qin, G. (2023) · Research Square · doi:10.21203/rs.3.rs-2875317/v1
Yuan, Z., & Li, X. (2023) · Research Square · doi:10.21203/rs.3.rs-3111105/v1
Lee, M. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.07076
Maki, W., Michihata, N., Hashimoto, Y., Matsui, H., Fushimi, K., & Yasunaga, H. (2023) · Annals of Clinical Epidemiology · doi:10.37737/ace.24004
Statistical inference for time‐to‐event data in non‐randomized cohorts with selective attrition
Wang, T., Mao, L., Cocco, A., & Kim, K. (2023) · Statistics in Medicine · doi:10.1002/sim.9952
Sex differences in the management of patients with suspected acute coronary syndrome in China
Cheng, K., Wang, J., Zheng, W., Wu, S., Zheng, J., Sang, W., Ma, J., Pang, J., Pan, C., Wang, G., et al. (2023) · Internal and Emergency Medicine · doi:10.1007/s11739-023-03494-3
“The probability of one patient belonging to the opposite group from the propensity score was used to calculate the overlap propensity weight [15].”
Leveraging Clinical Informatics to Address the Quintuple Aim for End-of-Life Care.
Zaleski, A. L., Craig, K. J. T., Caddigan, E., Yang, H., Cheng, Z., McNutt, S. L., & Baquet-Simpson, A. M. (2023) · PubMed Central
Léger, M. (2022) · theses.fr (ABES) · doi:10.70675/9bb005c0zfecfz46a6zaa16z03027138657c
Deng, P., Xu, H., Xing, Z., Deng, H., Li, Z., Deng, X., & Li, Y. (2024) · Research Square · doi:10.21203/rs.3.rs-4479846/v1
Saihara-Yamaguchi, A., Urushiyama, H., Makita, K., Aso, S., Watanabe, H., Yokoyama, A., Ando, T., Jo, T., Awano, N., Matsui, H., et al. (2024) · Respiratory Investigation · doi:10.1016/j.resinv.2024.09.005
Jia, Y., Zhang, Y., Chen, S., Jia, Z., Fang, T., Zhang, J., & Guo, Z. (2024) · Organ medicine. · doi:10.1002/orm2.10
Smaller Confidence Intervals From IPW Estimators via Data-Dependent CoarseningPreprint
Kalavasis, A., Mehrotra, A., & Zampetakis, M. (2024) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.2410.01658
Masuda, S., Fukasawa, T., Fujibayashi, S., Otsuki, B., Murata, K., Shimizu, T., Matsuda, S., & Kawakami, K. (2024) · Annals of Clinical Epidemiology · doi:10.37737/ace.25001
Temporal discontinuity trials and randomization: success rates versus design strength
Knaeble, B., & Kummerfeld, E. (2024) · Epidemiologic Methods · doi:10.1515/em-2023-0042
“We assume strong and well-defined preferences, i.e. extreme propensity probabilities, and as such our methodology is complementary to the methodology described in Li and Thomas [26] and Li et al. [27].”
MethodPrieto, M. (2024) · Hispania-revista Espanola De Historia · doi:10.3989/hispania.2024.019
Treatment Effect Estimation Using Observational Cohort and Nonrandomized Trial Data
Ren, J., & Cappelleri, J. C. (2024) · Springer eBooks · doi:10.1007/978-3-031-65937-9_10
Hu, J., Lu, Y., Zhao, J., Ma, D., Zhang, L., & Wei, J. C. (2025) · Arthritis & Rheumatology · doi:10.1002/art.43117
“7 There are many covariables in this article, and some covariables have large differences between the two groups, and they are still not balanced between the two groups even after weighting with the IPTW method.”
Duong, C.-H. (2024) · theses.fr (ABES) · doi:10.70675/2ffa46b0ze182z44c1zafadz81fde8ec0d22
Garneau, W. M., Wang, K., Liang, T., Xu, Y., Gladstone, D. E., Avery, R. K., D’Alessio, F. R., Robinson, M. L., Sahetya, S. K., Garibaldi, B. T., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-94024-y
“Use of overlap weighting based on the propensity score estimated from a logistic model leads to an exact balance for all covariates between different groups 16,17 .”
Ask why not: The case for on-table extubation in cardiac surgery
Pepe, R., Tobia, J. M., & Lee, L. Y. (2025) · Journal of Thoracic and Cardiovascular Surgery · doi:10.1016/j.jtcvs.2025.02.014
Multiply robust estimation of the average treatment effect based on overlap weighting
Hu, Y., Qin, G., & Yu, Y. (2025) · Communications in Statistics - Simulation and Computation · doi:10.1080/03610918.2025.2485382
“By definition, OW increases the relative weight of the individuals with PSs close to 0.5, allowing the overlapping population to contribute more information to the estimation (Li, Thomas, and Li 2019).”
InfluentialOud, L., & Garza, J. (2025) · Journal of Clinical Medicine Research · doi:10.14740/jocmr6189
“Thus, overlap weighting has been considered as effective as randomization if no adjustment was needed [50].”
Estimation of average treatment effects under missing data using generative adversarial networks
Shi, X., He, Z., Han, M., & Jiang, D. (2025) · Journal of the Korean Statistical Society · doi:10.1007/s42952-025-00327-1
Lee, E. H., Suh, Y. J., Park, J. W., Moon, J., Park, S. J., Lee, C. G., Yoon, H. I., Park, B. J., Lee, J. G., Kim, D. J., et al. (2025) · Cancers · doi:10.3390/cancers17122015
“A propensity score overlap weighting analysis [13] was performed to balance differences in baseline characteristics between patients who received SBRT and surgery.”
Financial pretrial release and innovations in outcome measurement
Terranova, V. A., & Slepicka, J. (2025) · Journal of Criminal Justice · doi:10.1016/j.jcrimjus.2025.102458
Liu, J., Lai, S., Lü, N., Luo, S., Tang, R., Li, L., Wu, P., Wang, D., & Tian, J. Q. (2025) · European journal of medical research · doi:10.1186/s40001-025-02658-5
“Hence, this research, utilizing a population-based cohort from the SEER database, sought to evaluate the effects of surgical interventions in individuals with BNEC through a PSOW analysis [10–14].”
Lee, Y., & Leite, W. L. (2026) · Behavior Research Methods · doi:10.3758/s13428-026-03024-x
“…samples or the PS model implements many confounders with missing indicators, inverse probability of treatment weighting (IPTW), a common approach for implementing PSA, is likely to have some extreme values, introducing treatment effect bias and excessive variance (Leite, 2017; Li & Thomas, 2019).”
Using Policy Learning to Inform Health Insurance Targeting: A Case Study of Indonesia
Shah, V., Jones, A. M., Malenica, I., Hidayat, T., & Kreif, N. (2025) · Health Economics · doi:10.1002/hec.70031
Martin, M., Lee, J., Gugig, R., Charville, G. W., & Barakat, M. T. (2025) · Surgeries · doi:10.3390/surgeries6040082
“The ASD is a measure of covariate balance [10].”
Beyond the Skin: Atopic Dermatitis and Increased Gastric Cancer Risk in Korea
Kang, H. S., Han, K. M., Kim, J. H., Kim, J. H., Choi, H. G., Yoo, D. M., Park, H. Y., Kim, N. Y., & Kwon, M. J. (2025) · Cancers · doi:10.3390/cancers17193214
“Overlap weights were assigned as 1—propensity score for individuals in the GC group and as propensity score for those in the control group [29].”
Serret-Larmande, A., Lambert, J., Gaudry, S., & Hajage, D. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.12241
“In practice, if an analyst has actually access to IPD from both trials, other estimands can be targeted which may be less subject to positivity issue depending on the context: Average Treatment Effect in the Treated, or Average Treatment Effect in the Overlap population [12].”
Association Between Atopic Dermatitis and Colorectal Cancer Risk: A Korean Population-Based Study
Kang, H. S., Han, K. M., Kim, J., Kim, J. H., Choi, H. G., Yoo, D. M., Park, H. Y., Kim, N. Y., & Kwon, M. J. (2025) · Biomedicines · doi:10.3390/biomedicines13102538
“…include the large sample size, comprehensive insurance data, and reduced selection bias through 1:4 matching, with additional validity from overlap-weighted logistic regression, which minimized bias, achieved excellent covariate balance [28], and strengthened confidence in the null association.”
van Wijk, E. J. C., Zugic, M., Rostami, S., van Gelder, M. M. H. J., Ahmad, A. S., Sitras, V., Spigset, O., Lupattelli, A., & Trinh, N. T. (2025) · Journal of Affective Disorders · doi:10.1016/j.jad.2025.120521
Lusk, J. B., Nalawade, V. V., Wilson, L. E., Yarnell, S. C., Song, A., Schrag, M., Poli, S., Hammill, B. G., Li, F., & Grory, B. M. (2025) · Journal of Internal Medicine · doi:10.1111/joim.70041
Self-citationCognitive Health Among Middle-aged and Older Adults in India - the Role of DepressionPreprint
Nadkarni, S., Banerjee, S., Putta, A., & Hanchate, A. D. (2025) · medRxiv · doi:10.1101/2025.11.12.25340069
Coënt, Q. L., Rosner, G. L., Wang, M. M., & Hu, C. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.14183
Han, K. M., Kang, H. S., Kim, J., Choi, H. G., Yoo, D. M., Kim, N. Y., Park, H. Y., & Kwon, M. J. (2025) · Cancers · doi:10.3390/cancers17223688
“Propensity scores were estimated via multivariable logistic regression including all covariates, and overlap weights were calculated by assigning a weight of 1–propensity score to individuals in the GC group and propensity score to those in the control group [37].”
Major study types with designs, measures, and examples
Abdelrashid, M., & Lobbous, M. (2025) · Elsevier eBooks · doi:10.1016/b978-0-323-90509-1.00041-2
Toyoshima, R., Aso, S., Matsui, H., Fushimi, K., Hama, N., Abe, R., Yasunaga, H., Sato, S., & Shibata, S. (2025) · The Journal of Dermatology · doi:10.1111/1346-8138.70082
“We calculated the propensity scores for receiving NSAIDs using a multivariable logistic regression analysis, which included the above covariates as the dependent variables [25–32].”
Okumura, K. (2025) · Journal of Vascular and Interventional Radiology · doi:10.1016/j.jvir.2025.107916
Wu, C., Kuo, S., Wang, C., Juan, Y., Wu, M., Huang, W., Wang, S., & Tsai, H. (2025) · Psychiatry and Clinical Neurosciences · doi:10.1111/pcn.70000
Peng, L., Chen, L., Wang, Z., Zhu, X., Sun, W., Wei-ping, W., & Lei, W. (2025) · Journal of Otolaryngology - Head and Neck Surgery · doi:10.1177/19160216251406522
Comparison of causal inference methods for observational data with a hierarchical structure
Kostouraki, A. (2024) · LSHTM Research Online (London School of Hygiene and Tropical Medicine) · doi:10.17037/pubs.04674980
Ren, J., Cislo, P. R., Cappelleri, J. C., Hlavacek, P., & DiBonaventura, M. (2024) · Figshare · doi:10.6084/m9.figshare.26561857
The post-authorisation safety of COVID-19 vaccines: real-world evidence
Li, X. (2024) · Oxford University Research Archive (ORA) (University of Oxford) · doi:10.5287/ora-jbgjpkwvd
Arrestier, R., Chaba, A., Mabrouki, A., Saccheri, C., Canet, E., de Chambrun, M. P., Stoclin, A., Picard, M., Wallet, F., Perier, F., et al. (2024) · Figshare · doi:10.6084/m9.figshare.26585571
A Study Comparing Different Routes of Myomectomy with Fertility Outcome
Singh, M., Verma, P., Gothwal, J., & Singh, M. K. (2023) · International Journal of Pharmaceutical and Clinical Research · doi:10.5281/zenodo.11266691
Lafaurie, M., Martin‐Blondel, G., Delobel, P., Kamar, N., Charpentier, S., Sommet, A., & Moulis, G. (2021) · Figshare · doi:10.6084/m9.figshare.14205306
Hu, W., Chen, S., Cai, J., Yang, Y., Yan, H., & Chen, F. (2024) · Figshare · doi:10.6084/m9.figshare.26728942
THE USE OF RANDOM FORESTS IN PROPENSITY SCORE WEIGHTING
Zheng, Y. (2023) · University Libraries (University of Maryland) · doi:10.13016/g5bl-rpbj
Ren, J., Cislo, P. R., Cappelleri, J. C., Hlavacek, P., & DiBonaventura, M. (2024) · Figshare · doi:10.6084/m9.figshare.26561854
Dupont, T., Darmon, M., Mariotte, É., Lemiale, V., Fadlallah, J., Mirouse, A., Zafrani, L., Azoulay, É., & Valade, S. (2022) · Figshare · doi:10.6084/m9.figshare.21430959
Ren, J., Cislo, P. R., Cappelleri, J. C., Hlavacek, P., & DiBonaventura, M. (2024) · Figshare · doi:10.6084/m9.figshare.26561860
Xu, H., Xing, Z., ai, K., Wang, J., Lv, Z., Deng, H., Li, K., Wang, Y., & Li, Y. (2024) · Figshare · doi:10.6084/m9.figshare.26671194
Hayashi, A., Mizuno, K., Shinkawa, K., Sakoda, K., Yoshida, S., Takeuchi, M., Yanagita, M., & Kawakami, K. (2024) · Figshare · doi:10.6084/m9.figshare.26697224
Koudmani, D. (2023) · UCL Discovery (University College London)
Individualized Learning for Crowdsourcing and Combination Treatments
Xu, Q. (2024) · eScholarship (California Digital Library)
Causal Inference Under Privacy Constraints
Yao, L. (2025) · DSpace@MIT (Massachusetts Institute of Technology)
Sahai, A., Koupenova, M., Freedman, J. E., & Cameron, S. (2020) · eScholarship@UMassChan
Causal quantile treatment effects at high and extreme quantile levels
Sun, S. (2023) · eScholarship@McGill (McGill) · doi:10.82308/5249
Shah, V. (2023) · White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York)
Covariate Adjustment in Modern Causal Design and Analysis
Liao, L. D. (2024) · eScholarship (California Digital Library)
Zonneveld-Heil, T. C. (2023) · Radboud Repository (Radboud University)
Propensity score weighting procedures for causal inference with clustered data
Fuentes Higuera, A. (2023) · MACAU: Open Access Repository of Kiel University (University Library Kiel)
Abreu, A. (2025) · Portuguese National Funding Agency for Science, Research and Technology (RCAAP Project by FCT) · doi:10.34626/jgke-0616
Chang, C.-R. (2024) · Digital Access to Scholarship at Harvard (DASH) (Harvard University)
Kang, J., Kim, H. J., Lark, A. R. S., Mir, F. A., Park, J., Son, Y., Fond, G. B., Boyer, L., Rahmati, M., Smith, L., et al. (2025) · Psychiatry Investigation · doi:10.30773/pi.2025.0234
“…between discrimination and drug use was particularly pronounced in specific subgroups, including younger individuals, those assigned female sex at birth, current smokers, individuals undergoing chemotherapy or immunotherapy, and those experiencing unemployment or COVID-19/flu-like symptoms.”
Hikasa, Y., Chaba, A., Culliver, C., Emel, H., Vo, T.-K., Yanase, F., Spano, S., Maeda, A., Eastwood, G. M., Kitisin, N., et al. (2026) · Heart Lung and Circulation · doi:10.1016/j.hlc.2025.05.103
Sakurai, K., Takeda, C., Tanaka-Mizuno, S., Mizota, T., Egi, M., & Kawakami, K. (2026) · Journal of Anesthesia · doi:10.1007/s00540-026-03664-5
“Individuals with propensity scores close to 0.5 have the greatest impact on the estimation of treatment effects, which decreases as the propensity score approaches 0 or 1 [16].”
InfluentialRichards‐Belle, A. (2025) · UCL Discovery (University College London)
Drucker, A. M., Bridgman, A. C., Imrit, M. A., Roberts, S. B., Tadrous, M., Stall, N. M., Fralick, M., Watt, J., Verma, A. A., & Razak, F. A. (2026) · Journal of the American Geriatrics Society · doi:10.1111/jgs.70323
Adani, M., Noirjean, S., Callegaro, A., Keshavan, P., & Costantini, M. (2026) · Pharmaceutical Statistics · doi:10.1002/pst.70069
“For this reason, it should be noted that OW changes the target population from the overall population represented by the sample (as targeted by IPW) to the “overlap” population [22].”
InfluentialQiao, J., Cao, R.-Y., & Li, X. (2026) · BMC Emergency Medicine · doi:10.1186/s12873-026-01483-1
“…that additionally tested an interaction term (treatment-by-location) to formally assess effect modification; (ii) propensity score matching (1:1 nearest neighbor, caliper = 0.2) to verify robustness; and (iii) unweighted multivariable logistic regression adjusted for the above covariates [17].”
InfluentialPropensity Score Matching and Clinical Interpretation
Okumura, K. (2026) · Radiology Imaging Cancer · doi:10.1148/rycan.250603
Eyasu, A. M., Zewotir, T. T., & Dessie, Z. G. (2026) · Wellbeing Space and Society · doi:10.1016/j.wss.2026.100366
Propensity score matching and clinical interpretation—comment on Araki et al.
Okumura, K. (2026) · Japanese Journal of Radiology · doi:10.1007/s11604-026-01959-x
Guo, W., Wang, M., Shin, J., Li, F., O'Brien, E. C., Glover, L. M., Bortfeld, K., Zhao, A., McDevitt, R. C., Kalapura, C., et al. (2026) · medRxiv · doi:10.64898/2026.02.18.26346594
Self-citationNi, Y., Li, S., Sun, N., Deng, Y., Yu, Z., Zha, L., & Wu, Y. (2026) · Archives of Public Health · doi:10.1186/s13690-025-01815-w
“Weights were calculated for participants with and without ACEs using the Overlap Weighting (OW) method, which reflects the probability of being assigned to the opposite group [34].”
EVALUATION OF ROBOTIC SURGERY AND PUBLIC PREFERENCE
Muaddi, H. (2022) · TSpace (University of Toronto)
Colacci, M. (2025) · TSpace (University of Toronto)
Vervoort, D., Dai, Y., Eddeen, A. B., Tuna, M., Austin, P. C., Ouzounian, M., Fremes, S. E., Lee, D. S., Wijeysundera, H. C., & Sun, L. Y. (2026) · CJC Open · doi:10.1016/j.cjco.2026.02.017
“26 The balance of baseline covariates between the CABG and PCI groups before and after weighting was assessed through standardized mean differences.”
InfluentialPark, S., Kim, S. B., Park, S. H., Kim, M., Lee, Y., Jin, S., Hur, K. Y., Kim, J. H., & Kim, G. (2026) · Diabetology & Metabolic Syndrome · doi:10.1186/s13098-026-02139-7
“Furthermore, overlap weighting was applied to reduce potential confounding and selection biases across the three body weight TTR groups, aiming to balance factors that might contribute to unintended weight regulation, such as severe chronic conditions or low income [20].”
Harada, M., Aso, S., Nimura, T., Yamaka, K., Aomura, D., Yamada, A., Sonoda, K., Yamaguchi, A., Kamimura, Y., Ichikawa, T., et al. (2026) · Journal of Personalized Medicine · doi:10.3390/jpm16030153
“Subsequently, overlap weighting was employed to achieve balance between the groups, as described by Li et al. [16].”
Yoo, D. M., Lee, H., Kang, H. S., Choi, H. G., Han, K. M., Kim, J. H., Bang, W. J., & Kwon, M. J. (2026) · Biomedicines · doi:10.3390/biomedicines14030613
“Overlap weights were then derived, assigning greater weights to participants with similar probabilities of belonging to either group (gout, IBD, or control), thereby improving comparability and preserving a larger effective sample size compared with conventional matching [35,36].”
Huang, L., & Yi, M. (2026) · BMC Nephrology · doi:10.1186/s12882-026-04842-z
“The use of propensity score methods represents contemporary approaches to strengthening causal inference from observational data by mimicking attributes of randomized trials through covariate balancing, though residual confounding from unmeasured factors remains possible [31, 32].”
Ishaqui, A. A., Alsaleh, E. A., Khalil, A. A. A., Kaddoura, M. A., Orayj, K. M., Asiri, R., Alshahrani, S. M., Ahmad, S. A., Kumar, N., Iqbal, A., et al. (2026) · Naunyn-Schmiedeberg s Archives of Pharmacology · doi:10.1007/s00210-026-05184-1
“Overlap weighting targets the subpopulation in which treated and untreated patients have the greatest covariate overlap which improves comparability and reduces reliance on extreme weights (Li et al. 2019).”
Yasuda, Y., Yoshida, S., Yajima, S., Yamaguchi, Y., Chen, W., Tanaka, H., Sato, H., Hirakawa, A., Suzuki, K., Ishihara, K., et al. (2026) · The Prostate · doi:10.1002/pros.70159
“Because treatment allocation was not randomized in routine practice and substantial confounding by indication was anticipated, we prespecified causal adjustment using propensity‐score modeling with overlap weighting [16].”
Suzuki, S., Arita, R., Obara, T., Ishikawa, T., Kunitoki, T., Sakai, T., Noda, A., Shinoda, G., Ishikuro, M., Orui, M., et al. (2026) · Traditional & Kampo Medicine · doi:10.1002/tkm2.70049
Wang, T.-H., Chien, S., Cheng, W., Huang, Y.-W., Wang, S., Huang, W., Tzeng, Y., Hsu, C.-C., Chen, W. J., & Wu, C. (2026) · Journal of Mental Health · doi:10.1080/09638237.2026.2645540
“Propensity score weighting using overlap weights (Li et al., 2019) was utilized to address baseline characteristic disparities between early retirees and the employed group.”
Park, C. M., Shi, S., Chen, X., Parks, A. L., & Kim, D. H. (2026) · American Journal of Hematology · doi:10.1002/ajh.70302
“Propensity score overlap weighting was applied to balance characteristics [29, 30].”
Wee, L. E., Malek, M. I. B. A., Ho, R. W. L., Lim, J. T., Chiew, C. J., Li, R., Chong, C. Y., Choolani, M. A., Lye, D. C., & Tan, K. B. (2026) · Clinical Microbiology and Infection · doi:10.1016/j.cmi.2026.03.027
Cheng, M.-C., Chen, P., Chen, Y., Lai, S., Chen, J.-H., Dai, M., & Chang, P. (2026) · Life · doi:10.3390/life16040564
“Third, the use of overlap weights is particularly appropriate for our sample given the imbalanced group sizes and potential positivity violations with extreme propensity scores [31,32].”
Chatha, Z. F., Trinh, N. T., Rostami, S., Bergink, V., Carson, A. C., Magnus, P. M., & Lupattelli, A. (2026) · The European Journal of Psychiatry · doi:10.1016/j.ejpsy.2026.100352
Tomoaki, I. D. A. (2024) · Institutional Repositories DataBase (IRDB) · doi:10.20776/900122910
Metadata
- Authors
- Li, F., & Thomas, L. E.
- Affiliations
- Duke University (US)
- Corresponding author
- Li, Fan
- Venue
- American Journal of Epidemiology
- Publisher
- Oxford University Press (OUP)
- Published
- 2018-09-05
- Volume
- 188
- Issue
- 1
- Pages
- 189-190
- ISSN
- 0002-9262 (ISSN-L)
- 1476-6256
- OpenAlex
- W2907932858
- Cited by
- 694
- References
- 19
- Citations by year
- 2026: 97 · 2025: 124 · 2024: 145 · 2023: 119 · 2022: 83 · 2021: 73 · 2020: 35 · 2019: 15 · 2018: 1
- FWCI
- 25.73
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- academic.oup.com/journals/pages/open_access/funder_policies/chorus/standard_publication_model (am)
- Locations
- American Journal of Epidemiology (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Agency for Healthcare Research and Quality (SES-1424688)
- National Science Foundation
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Keywords
- inverse probability weighting, treatment effect estimation, bias and variance, confidence interval coverage, standard error estimation, causal inference
- MeSH terms
- Epidemiologic Methods, Humans, Models, Statistical, Bias, Causality, 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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.