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 101–200 of 1,000
McCormick, N., Yokose, C., Lu, N., Wexler, D. J., Aviña-Zubieta, J. A., Vera, M. A. D., Chigurupati, S., Tan, K., Chen, C., McCoy, R. G., et al. (2024) · BMJ · doi:10.1136/bmj-2024-080035 · Cited by 34
“60 61 The overlap weighting estimate can be interpreted as the average treatment effect in the overlap population, representing patients with a realistic likelihood of receiving either treatment.”
Abécassis, J., Dumas, É., Alberge, J., & Varoquaux, G. P. (2025) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-103123-095750 · Cited by 34
Miyamoto, Y., Ohbe, H., Kumazawa, R., Matsui, H., Fushimi, K., Yasunaga, H., & Ohta, B. (2023) · JAMA Dermatology · doi:10.1001/jamadermatol.2023.0035 · Cited by 33
Grory, B. M., Sun, J., Alhanti, B., Lusk, J. B., Li, F., Adeoye, O. M., Furie, K. L., Hasan, D. M., Messe, S. R., Sheth, K. N., et al. (2024) · JAMA Neurology · doi:10.1001/jamaneurol.2024.3659 · Cited by 32
Self-citationLee, J. S., Escano, R. S., Therrien, N. L., Kumar, A., Bhatt, A., Pollack, L. M., Jackson, S. L., & Luo, F. (2024) · Journal of the American Heart Association · doi:10.1161/jaha.124.037357 · Cited by 33
“37,38 We calculated overlap weights that were proportional to the probability of individuals belonging to the opposite group.”
Rizk, J. G. (2025) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2025.111942 · Cited by 33
Dominici, F., Bargagli-Stoffi, F. J., & Mealli, F. (2021) · Harvard Data Science Review · doi:10.1162/99608f92.8102afed · Cited by 32
“…directly optimize weights or find optimal subsets of controls such that the mean or other characteristics of the covariates is the same in the treatment and control group (Diamond & Sekhon, 2013; F. Li et al., 2018; F. Li & Thomas, 2018; Zubizarreta, 2012, 2015; Zubizarreta, Paredes, et al., 2014).”
BackgroundRoute of myomectomy and fertility: a prospective cohort study
Wise, L. A., Thomas, L. E., Anderson, S., Baird, D. D., Anchan, R. M., Terry, K. L., Marsh, E. E., Wegienka, G., Nicholson, W. K., Wallace, K. L., et al. (2022) · Fertility and Sterility · doi:10.1016/j.fertnstert.2022.01.013 · Cited by 33
Self-citationVarga, A. N., Morel, A. E. G., Lokkerbol, J., van Dongen, J. M., van Tulder, M. W., & Bosmans, J. E. (2022) · Statistics in Medicine · doi:10.1002/sim.9628 · Cited by 33
Montelukast Use and the Risk of Neuropsychiatric Adverse Events in Children
Wintzell, V., Brenner, P., Halldner, L., Rhedin, S., Gong, T., & Almqvist, C. (2025) · Archives of Pediatrics and Adolescent Medicine · doi:10.1001/jamapediatrics.2024.5429 · Cited by 31
Lee, S., Hwang, S. H., Park, S., Son, Y., Kim, S., Kim, H. J., Park, J., Jo, H., Lee, K., Oh, J., et al. (2025) · Circulation · doi:10.1161/circulationaha.125.073086 · Cited by 31
Weld, G., West, P., Glenski, M., Arbour, D. T., Rossi, R. A., & Althoff, T. (2022) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v16i1.19362 · Cited by 31
A Review of Causal Inference for External Comparator Arm Studies
Rippin, G., Ballarini, N. M., Sanz, H., Largent, J. A., Quinten, C., & Pignatti, F. (2022) · Drug Safety · doi:10.1007/s40264-022-01206-y · Cited by 31
Nicholson, W. K., Wegienka, G., Zhang, S., Wallace, K. L., Stewart, E. A., Laughlin-Tommaso, S. K., Thomas, L. E., Jacoby, V. L., Marsh, E. E., Wise, L. A., et al. (2019) · Obstetrics and Gynecology · doi:10.1097/aog.0000000000003354 · Cited by 31
Self-citationChaumont, C., Hayoun, C., Savouré, A., Hamoud, R. A., Auquier, N., McDonnell, E., Eltchaninoff, H., & Anselme, F. (2024) · Journal of the American Heart Association · doi:10.1161/jaha.123.033146 · Cited by 30
Fu, E. L., Clase, C. M., Janse, R. J., Lindholm, B., Dekker, F. W., Jardine, M., & Carrero, J. J. (2022) · International Journal of Cardiology · doi:10.1016/j.ijcard.2022.01.042 · Cited by 30
Differences in target estimands between different propensity score‐based weights
Austin, P. C. (2023) · Pharmacoepidemiology and Drug Safety · doi:10.1002/pds.5639 · Cited by 30
Clinical and Prognostic Factors in Patients with IgG4-Related Kidney Disease
Chaba, A., Devresse, A., Audard, V., Boffa, J. J., Karras, A., Cartery, C., Deltombe, C., Chemouny, J., Contamin, C., Courivaud, C., et al. (2023) · Clinical Journal of the American Society of Nephrology · doi:10.2215/cjn.0000000000000193 · Cited by 31
“↗ IgG1, n (%) 29 (44) ↗ IgG2, n (%) 19 (28) ↗ IgG3, n (%) 25 (38) Serum complement dosage, n (%) 82 (81) ↘ C3 or ↘ C4, n (%) 37 (45) ↘ C3, n (%) 33 (40) ↘ C4, n (%) 32 (39) Antinuclear antibodies dosage, n (%) 97 (96) Positive, n (%) 35 (36) ANCA dosage, n (%) 81 (80) Positive, n (%) 18 (22) C-reactive protein, mg/L,…”
Barayev, O., Hawley, C. E., Wellman, H., Gerlovin, H., Hsu, W., Paik, J. M., Mandel, E. I., Liu, C., Djoussé, L., Gaziano, J. M., et al. (2023) · JAMA Network Open · doi:10.1001/jamanetworkopen.2023.46373 · Cited by 30
First Trimester Use of Buprenorphine or Methadone and the Risk of Congenital Malformations
Suarez, E. A., Bateman, B. T., Straub, L., Hernández–Díaz, S., Jones, H. E., Gray, K. J., Connery, H. S., Davis, J. M., Lester, B. M., Terplan, M., et al. (2024) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2023.6986 · Cited by 30
Reconsidering Generative Objectives For Counterfactual Reasoning
Lu, D., Tao, C., Chen, J., Li, F., Guo, F., & Carin, L. (2020) · neural information processing systems · Cited by 30
Self-citationSakamoto, T., Fujiogi, M., Ishimaru, M., Matsui, H., Fushimi, K., & Yasunaga, H. (2021) · Hernia · doi:10.1007/s10029-021-02439-z · Cited by 30
Otaka, S., Aso, S., Matsui, H., Fushimi, K., & Yasunaga, H. (2020) · European Journal of Trauma and Emergency Surgery · doi:10.1007/s00068-020-01548-1 · Cited by 29
“Furthermore, one study has shown that overlap weights may be more efficient than inverse probability of treatment weighting and propensity score with trimming [20].”
BackgroundMethodImai, S., Inoue, N., & Nagai, H. (2022) · BMC Infectious Diseases · doi:10.1186/s12879-022-07548-3 · Cited by 29
Masuda, S., Fukasawa, T., Takeuchi, M., Fujibayashi, S., Otsuki, B., Murata, K., Shimizu, T., Matsuda, S., & Kawakami, K. (2022) · Clinical Orthopaedics and Related Research · doi:10.1097/corr.0000000000002322 · Cited by 29
“To determine which procedure had the higher revision rate, we used a propensity score overlap weighting analysis to adjust for measured confounders such as age, sex, comorbidities, and hospital type between the microendoscopic discectomy and microdiscectomy or open discectomy groups [14].”
BackgroundMethodTranscatheter vs Surgical Aortic Valve Replacement in Pure Native Aortic Regurgitation
Mentias, A. G., Saad, M. S., Menon, V., Reed, G. W., Popović, Z., Johnston, D. R., Rodríguez, L., Gillinov, M., Griffin, B. P., Jneid, H. M., et al. (2022) · The Annals of Thoracic Surgery · doi:10.1016/j.athoracsur.2022.09.016 · Cited by 29
Transcatheter Versus Surgical Aortic Valve Replacement in Patients With Rheumatic Aortic Stenosis
Mentias, A. G., Saad, M. S., Desai, M. Y., Krishnaswamy, A., Menon, V., Horwitz, P. A., Kapadia, S. R., & Vaughan‐Sarrazin, M. (2021) · Journal of the American College of Cardiology · doi:10.1016/j.jacc.2021.02.032 · Cited by 30
Randomization Tests to Assess Covariate Balance When Designing and Analyzing Matched Datasets
Branson, Z. (2021) · Observational Studies · doi:10.1353/obs.2021.0031 · Cited by 32
Prolonged inhalation of cadmium.
Princi, F., & Geever, E. F. (1950) · PubMed · Cited by 29
Poizeau, F., Kerbrat, S., Balusson, F., Tattevin, P., Revest, M., Cattoir, V., Paz, D. L., Lesimple, T., Pracht, M., Dinulescu, M., et al. (2022) · JNCI Journal of the National Cancer Institute · doi:10.1093/jnci/djac019 · Cited by 29
Overlap, matching, or entropy weights: what are we weighting for?
Matsouaka, R., Liu, Y., & Zhou, Y. (2024) · Communications in Statistics - Simulation and Computation · doi:10.1080/03610918.2024.2319419 · Cited by 28
“Additional insights on the equipoise estimators can be find in the references hereafter (Li, Thomas, and Li 2018; Matsouaka and Zhou, 2020; Thomas, Li, and Pencina 2020).”
InfluentialAdaptive debiased machine learning using data-driven model selection techniquesPreprint
van der Laan, L. W. P., Carone, M., Luedtke, A. R., & van der Laan, M. J. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.12544 · Cited by 28
“Previous studies have suggested using easier-to-estimate target parameters that incorporate prespecified (working) model assumptions, such as treatment effect homogeneity or a known parametric form (Crump et al., 2006; Petersen et al., 2012; Li et al., 2019).”
BackgroundMethodLi, H., Wallace, Z. S., Sparks, J. A., Lu, N., Wei, J., Xie, D., Wang, Y., Zeng, C., Lei, G., & Zhang, Y. (2022) · Arthritis Care & Research · doi:10.1002/acr.25028 · Cited by 27
“Overlap weights were bounded and smoothly reduced the influence of individuals at the tails of the exposure score distribution without making any exclusions (27,28).”
Association Between Treatment of Secondary Hyperparathyroidism and Posttransplant Outcomes
Mathur, A., Sutton, W., Ahn, J. B., Prescott, J. D., Zeiger, M. A., Segev, D. L., & McAdams-DeMarco, M. (2021) · Transplantation · doi:10.1097/tp.0000000000003653 · Cited by 26
“All models were weighted using propensity score to adjust for confounding.(24) As some transplant-related factors and all donor-related factors are typically determined after the treatment of interest, they might not meet the conditions for being confounders.”
MethodChen, H., Sun, C., Lee, C., Wu, I., Chen, Y., Lin, Y., Fang, W.-C., & Pan, H. (2021) · Clinical Nutrition · doi:10.1016/j.clnu.2021.01.045 · Cited by 26
DrugWAS: Drug‐wide Association Studies for COVID‐19 Drug Repurposing
Bejan, C. A., Cahill, K. N., Staso, P. J., Choi, L., Peterson, J. F., & Phillips, E. J. (2021) · Clinical Pharmacology & Therapeutics · doi:10.1002/cpt.2376 · Cited by 26
Luk, A. O. Y., Yip, T. C., Zhang, X., Kong, A. P. S., Wong, V. W., Ronald, C. W., & Wong, G. L. (2021) · BMJ Open · doi:10.1136/bmjopen-2021-052310 · Cited by 26
Kwon, M. J., Kang, H. S., Kim, J., Kim, J. H., Kim, S. H., Kim, N. Y., Nam, E. S., Min, K., & Choi, H. G. (2021) · Pharmaceuticals · doi:10.3390/ph14121283 · Cited by 26
Association Between Telomere Length and Skin Cancer and Aging: A Mendelian Randomization Analysis
Song, N., Cui, Y., & Wang, X. (2022) · Frontiers in Genetics · doi:10.3389/fgene.2022.931785 · Cited by 26
“IVW methods are susceptible to being hampered by extreme propensity scores, leading to biased estimates and excessive variance (Li et al., 2019).”
Chao, T.-C., Tung, H.-Y., Tsai, C., de la Peñ, C. G., Wu, C.-C., Liao, C.-H., Ou, Y.-C., Tsai, C.-R., Yang, S.-D., & Tsai, Y. (2023) · Hernia · doi:10.1007/s10029-023-02916-7 · Cited by 26
Long-Term Postoperative Outcomes by Surgeon Gender and Patient-Surgeon Gender Concordance in the US
Ikesu, R., Gotanda, H., Russell, T. A., Maggard-Gibbons, M. A., Russell, M. M., Yoshida, R., Li, R., Klomhaus, A. M., de Virgilio, C., & Tsugawa, Y. (2025) · JAMA Surgery · doi:10.1001/jamasurg.2025.0866 · Cited by 25
Yamamoto, A., Gelberg, L., Needleman, J., Kominski, G. F., Vangala, S., Miyawaki, A., & Tsugawa, Y. (2021) · JAMA Network Open · doi:10.1001/jamanetworkopen.2021.7491 · Cited by 25
Two-stage matching-adjusted indirect comparison
Remiro‐Azócar, A. (2022) · BMC Medical Research Methodology · doi:10.1186/s12874-022-01692-9 · Cited by 25
“Near-violations of positivity between treatment arms may lead to extreme inverse probability of treatment weights [80], further inflating variance in 2SMAIC.”
BackgroundUsing propensity scores for racial disparities analysis
Li, F., & Li, F. (2023) · Observational Studies · doi:10.1353/obs.2023.0005 · Cited by 26
Self-citationNew statin use, mortality, and first cardiovascular events in older US Veterans by frailty status
Orkaby, A. R., Lü, B., Ho, Y.-L. A., Treu, T. M., Galloway, A., Wilson, P. W. F., Cho, K., Gaziano, J. M., Alexander, K. P., GAGNON, D. R., et al. (2023) · Journal of the American Geriatrics Society · doi:10.1111/jgs.18700 · Cited by 27
“26 Cox proportional hazards models were fit to evaluate association of statin use with outcomes, using overlap weighting.”
MethodMcCormick, N., Yokose, C., Lu, N., Wexler, D. J., Aviña-Zubieta, J. A., Vera, M. A. D., McCoy, R. G., & Choi, H. K. (2024) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2024.0376 · Cited by 25
Wee, L. E., Lim, J. T., Tay, A. T., Chiew, C. J., Ong, B., Lye, D. C., Lahiri, M., & Tan, K. B. (2024) · JAMA Network Open · doi:10.1001/jamanetworkopen.2024.30983 · Cited by 25
Boujibar, F., Gillibert, A., Bonnevie, T., Rinieri, P., Montagne, F., Selim, J., Cuvelier, A., Gravier, F., & Baste, J. (2022) · Journal of physiotherapy · doi:10.1016/j.jphys.2022.03.001 · Cited by 25
Safety of influenza vaccine during COVID-19
Zein, J., Whelan, G., & ERZURUM, S. C. (2020) · Journal of Clinical and Translational Science · doi:10.1017/cts.2020.543 · Cited by 24
“The overlap propensity score weighting method was then applied to directly compare weighted groups on the outcomes of interest [3].”
MethodCausal inference for quantile treatment effects
Sun, S., Moodie, E. E. M., & Nešlehová, J. (2021) · Environmetrics · doi:10.1002/env.2668 · Cited by 24
“This type of behavior has also been observed in the context of the ATEs (see (Li & Li, 2019; Li, Thomas, & Li, 2018)).”
BackgroundInfluentialGressens, S. B., Esnault, V., Castro, N. D., Sellier, P., Sène, D., Chantelot, L., Hervier, B., Delaugerre, C., Chevret, S., Molina, J., et al. (2022) · PLoS ONE · doi:10.1371/journal.pone.0262564 · Cited by 24
“In order to account for indication bias resulting from potential differences between the two treatment groups (dexamethasone alone or dexamethasone with remdesivir), a propensity score matching analysis was performed with the main analysis to assess primary and secondary outcomes conducted on the matched populations […”
MethodMateos, M., Weisel, K. C., Martin, T. G., Berdeja, J. G., Jakubowiak, A. J., Stewart, A. K., Jagannath, S., Lin, Y., Diels, J., Ghilotti, F., et al. (2022) · Haematologica · doi:10.3324/haematol.2022.280482 · Cited by 24
Wee, L. E., Lim, J. T., Ho, R. W. L., Chiew, C. J., Young, B. E., Venkatachalam, I., Sim, J. X. Y., Cheong, H. Y., Ng, T. Y., Yung, C.-F., et al. (2025) · The Lancet Regional Health - Western Pacific · doi:10.1016/j.lanwpc.2025.101494 · Cited by 24
Propensity score analysis revisited
Hashimoto, Y., & Yasunaga, H. (2025) · Annals of Clinical Epidemiology · doi:10.37737/ace.25012 · Cited by 24
Severe Maternal and Neonatal Morbidity Among Gestational Carriers: A Cohort Study
Vélez, M. P., Ivanova, M., Shellenberger, J. P., Pudwell, J., & Ray, J. G. (2024) · Annals of Internal Medicine · doi:10.7326/m24-0417 · Cited by 23
“Propensity score (PS) – based overlap weights (OWs) were used to create cohorts that were balanced across baseline characteristics (12).”
Adult criminal outcomes of juvenile justice involvement
Copeland, W., Tong, G., Gifford, E. J., Easter, M. M., Shanahan, L., Swartz, M. S., & Swanson, J. W. (2022) · Psychological Medicine · doi:10.1017/s0033291722000393 · Cited by 24
“Propensity score methods can improve the covariate balance through matching, weighting, or stratification, to make causal inferences or to reduce confounding in observational studies (Li & Li, 2019; Rosenbaum & Rubin, 1983; VanderWeele, 2006).”
BackgroundMethodPaciotti, M., Alkhatib, K. Y., Nguyen, D., Yim, K. H., Lipsitz, S. R., Mossanen, M., Casale, P., Pierorazio, P. M., Kibel, A. S., Trinh, Q., et al. (2023) · Cancers · doi:10.3390/cancers15051373 · Cited by 23
“PSOW improves the balance and precision at the baseline relative to other conventional propensity score methods [16,17].”
MethodLocal Gaussian Process Extrapolation for BART Models with Applications to Causal Inference
Wang, M., He, J., & Hahn, P. R. (2023) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2023.2240384 · Cited by 23
“Li, Morgan, and Zaslavsky (2018) and Li, Thomas, and Li (2018) proposed using overlap weights to balance the covariates for estimating the ATE.”
BackgroundHanberg, J. S., Fu, X., Wang, X., Patel, N. J., Kawano, Y., Schiff, A. E., Kowalski, E., Cook, C., Vanni, K. M. M., Guzzo, K., et al. (2023) · The Lancet Rheumatology · doi:10.1016/s2665-9913(23)00272-2 · Cited by 24
Keller, B., & Branson, Z. (2024) · Asia Pacific Education Review · doi:10.1007/s12564-024-09957-2 · Cited by 24
Kashiwagi, S., Kanda, N., Yoshida, M., Wakimoto, Y., Ohbe, H., & Nakamura, K. (2024) · Clinical Nutrition · doi:10.1016/j.clnu.2024.06.033 · Cited by 23
Ono, S., Ishimaru, M., Yokota, I., Konishi, T., Okada, A., Ono, Y., Matsui, H., Itai, S., Yonenaga, K., Tonosaki, K., et al. (2022) · Thrombosis Research · doi:10.1016/j.thromres.2022.12.007 · Cited by 22
Covariate adjustment in randomized clinical trials with missing covariate and outcome data
Chang, C., Song, Y., Li, F., & Wang, R. (2023) · Statistics in Medicine · doi:10.1002/sim.9840 · Cited by 23
Self-citationKreutz, R. H., Deray, G., Floege, J., Gwechenberger, M., Hahn, K., Luft, A. R., Persson, P. B., Axthelm, C., Beer, J. H., Bergler-Klein, J. K., et al. (2024) · JACC Advances · doi:10.1016/j.jacadv.2023.100813 · Cited by 22
Quantifying and Exploring Elementary School Excellence Gaps Across Schools and Time
Rambo-Hernandez, K. E., Peters, S. J., & Plucker, J. A. (2019) · Journal of Advanced Academics · doi:10.1177/1932202x19864116 · Cited by 22
“By weighting the Level 2 estimates by the smaller group, we were able to account for variability in the precision of the excellence gap estimates and also for extreme variability likely to occur due to estimates based on very few students (Li et al., 2018).”
BackgroundPropensity Score Weighting Analysis of Survival Outcomes Using Pseudo-Observations
Zeng, S., Li, F., Hu, L., & Li, F. (2021) · Statistica Sinica · doi:10.5705/ss.202021.0175 · Cited by 22
“Second, the IPW estimator with pseudo-observations corresponds to a target population that is represented by the study sample, but the interpretation of such a population is often questionable in the case of a convenience sample (Li et al., 2019).”
MethodSelf-citationKaradsheh, M. J., Tyrell, R. O., Deng, M., Egleston, B. L., Krupp, J. C., Shafqat, M. S., & Patel, S. A. (2021) · Breast Cancer Research and Treatment · doi:10.1007/s10549-020-06073-8 · Cited by 21
“Covariates were adjusted using propensity score-based overlap weighting [12].”
MethodAddressing positivity violations in causal effect estimation using Gaussian process priors
Zhu, Y., Mitra, N., & Roy, J. (2022) · Statistics in Medicine · doi:10.1002/sim.9600 · Cited by 21
“(2018) proposed estimating causal effects using overlap weights.(13;14) However, overlap weights involve propensity score estimation and place more emphasis on those with higher probabilities of receiving either treatment.”
BackgroundYin, X., Mishra-Kalyan, P. S., Sridhara, R., Stewart, M. D., Stuart, E. A., & Davi, R. C. (2022) · Journal of Biopharmaceutical Statistics · doi:10.1080/10543406.2021.2011901 · Cited by 21
Brumbaugh, J. E., Ball, C. T., Crook, J. E., Stoppel, C. J., Carey, W. A., & Bobo, W. V. (2023) · Mayo Clinic Proceedings Innovations Quality & Outcomes · doi:10.1016/j.mayocpiqo.2023.02.002 · Cited by 21
Using Balancing Weights to Target the Treatment Effect on the Treated when Overlap is Poor
Ben‐Michael, E., & Keele, L. J. (2023) · Epidemiology · doi:10.1097/ede.0000000000001644 · Cited by 21
“Li, F., L. E. Thomas, and F. Li (2019).”
Turner, E. L., Yao, L., Li, F., & Prague, M. (2019) · Statistical Methods in Medical Research · doi:10.1177/0962280219859915 · Cited by 21
“the probability of being observed is very small), this can lead to instability and strategies such as trimming or truncation may need to be used.(12,60) Third, in the small sample case (k <20), there may be bias in estimating the weights for CW-GEE because they are estimated using a random effects logistic regression…”
MethodSelf-citationComparative effectiveness of oral anticoagulants in everyday practice
Camm, A. J., Fox, K. A. A., Virdone, S., Bassand, J., Fitzmaurice, D. A., Berchuck, S. I., Gersh, B. J., Goldhaber, S. Z., Goto, S., Haas, S. K., et al. (2021) · Heart · doi:10.1136/heartjnl-2020-318420 · Cited by 21
Mannino, D. M., Weng, S. F., Germain, G., Boudreau, J., Tardif‐Samson, A., Forero-Schwanhaeuser, S., Laliberté, F., Gravelle, P., Compton, C. H., Noorduyn, S. G., et al. (2024) · Advances in Therapy · doi:10.1007/s12325-024-03088-1 · Cited by 20
Schellongowski, P., Darmon, M., Eller, K., Munshi, L., Liebregts, T., Metaxa, V., Montini, L. M., Lahmer, T., Taccone, F. S., de Louw, A. V., et al. (2025) · Intensive Care Medicine · doi:10.1007/s00134-025-08113-7 · Cited by 20
“The analysis emphasizes the proportion of the population where the most treat-ment equipoise exists in clinical practice [25].”
Cleman, J., Romain, G., Grubman, S., Guzman, R. J., Smolderen, K. G. E., & Mena‐Hurtado, C. (2023) · Journal of Vascular Surgery · doi:10.1016/j.jvs.2023.05.015 · Cited by 20
Kostouraki, A., Hajage, D., Rachet, B., Williamson, E., Chauvet, G., Belot, A., & Leyrat, C. (2024) · Statistics in Medicine · doi:10.1002/sim.10078 · Cited by 20
“This new population of interest can be defined as those who achieve the “most overlap in observed characteristics between treatment groups,” to cite Li et al. 15 In this situation, one targets the ATE in the overlap population or often described as the equipoise population (ATO).”
BackgroundGerschenfeld, G., Turc, G., Obadia, M., Chausson, N., Consoli, A., Olindo, S., Caroff, J., Marnat, G., Blanc, R., Hassen, W. B., et al. (2024) · Neurology · doi:10.1212/wnl.0000000000209398 · Cited by 20
Wee, L. E., Lim, J. T., Tan, J. Y. J., Malek, M. I. B. A., Chiew, C. J., Ng, L. C., Chia, P. Y., Leo, Y., Lye, D. C., & Tan, K. B. (2024) · Journal of Travel Medicine · doi:10.1093/jtm/taae081 · Cited by 20
Straub, L., Bateman, B. T., Hernández–Díaz, S., Zhu, Y., Suarez, E. A., Vine, S. M., Jones, H. E., Connery, H. S., Davis, J. M., Gray, K. J., et al. (2024) · JAMA · doi:10.1001/jama.2024.11501 · Cited by 20
Who Are We Missing? : A Principled Approach to Characterizing the Underrepresented Population
Parikh, H., Ross, R. K., Stuart, E. A., & Rudolph, K. E. (2025) · Journal of the American Statistical Association · doi:10.1080/01621459.2025.2495319 · Cited by 20
“The traditional selection score-based approaches are akin to an approach proposed in Crump et al. (2009) and Li, Thomas, and Li (2019) to identify underrepresented populations using ( x ) , and in particular the normalized selection odds, that is, (cid:4)( x )/(cid:4) .”
Adbi, A., & Shukla, D. (2022) · Journal of International Business Studies · doi:10.1057/s41267-022-00532-8 · Cited by 19
Szatkowski, L., Sharkey, D., Budge, H., & Ojha, S. (2023) · EClinicalMedicine · doi:10.1016/j.eclinm.2023.102296 · Cited by 19
“In a sensitivity analysis, we used overlap weights 18 derived from the propensity scores to weight the calculation of odds ratios for adverse outcomes in the full cohort, such that all infants contributed to the analysis with their contribution proportional to their overlap weight.”
MethodWhen does adjusting covariate under randomization help? A comparative study on current practices
Gao, Y., Liu, Y., & Matsouaka, R. (2024) · BMC Medical Research Methodology · doi:10.1186/s12874-024-02375-3 · Cited by 19
Nakamizo, T., Kanda, T., Kudo, Y., Sugawara, E., Hashimoto, E., Okazaki, A., Usuda, M., Nagai, T., Hara, H., & Johkura, K. (2020) · Journal of the Neurological Sciences · doi:10.1016/j.jns.2020.117251 · Cited by 19
Saade, A., Bourmaud, A., Schnell, D., Darmon, M., & for the R2D2 Study Group (2021) · Critical Care Medicine · doi:10.1097/ccm.0000000000005372 · Cited by 19
“This method assigns higher weight to patients with intermediate risk and lower weight to outliers from both groups, consequently emphasizing the proportion of intermediate risk patients, assumed to reflect a higher degree of uncertainty/equipoise (29).”
MethodPope, M. K., Hall, T. S., Schirripa, V., Radić, P., Virdone, S., Pieper, K. S., Heuzey, J. L., Janský, P., Fitzmaurice, D. A., Cappato, R., et al. (2021) · BMJ · doi:10.1136/bmj-2021-066450 · Cited by 19
Li, F., Hong, H., & Stuart, E. A. (2021) · Communication in Statistics- Theory and Methods · doi:10.1080/03610926.2021.2020291 · Cited by 19
Self-citationRE:“ADDRESSING EXTREME PROPENSITY SCORES VIA THE OVERLAP WEIGHTS”
Li, F., Thomas, L. E., & Li, F. (2020) · American Journal of Epidemiology · doi:10.1093/aje/kwaa229 · Cited by 19
“(1) regarding asymmetric trimming and demonstrate the validity of asymmetric trimming under lack of overlap.”
BackgroundMethodInfluentialSelf-citationDo “Real World” Childhood Mental Health Services Reduce Risk for Adult Psychiatric Disorders?
Copeland, W., Tong, G., & Shanahan, L. (2022) · Journal of the American Academy of Child & Adolescent Psychiatry · doi:10.1016/j.jaac.2021.12.014 · Cited by 18
Einhorn, L. M., Andrew, B. Y., Nelsen, D. A., & Ames, W. A. (2022) · Journal of Cardiothoracic and Vascular Anesthesia · doi:10.1053/j.jvca.2022.07.014 · Cited by 18
Choi, H. G., Kwon, M. J., Kim, J. H., Kim, S. Y., Kim, J.-H., Park, J. Y., Hwang, Y. I., & Jang, S. H. (2024) · World Allergy Organization Journal · doi:10.1016/j.waojou.2024.100907 · Cited by 18
Nirmatrelvir/ritonavir treatment and risk for postacute sequelae of COVID-19 in older Singaporeans
Wee, L. E., Lim, J. T., Tay, A. T., Chiew, C. J., Young, B. E., Wong, B., Lim, R., Lee, C. L., Tan, J. Y. S., Vasoo, S. S., et al. (2024) · Clinical Microbiology and Infection · doi:10.1016/j.cmi.2024.08.019 · Cited by 18
Average treatment effect on the treated, under lack of positivity
Liu, Y., Li, H., Zhou, Y., & Matsouaka, R. (2024) · Statistical Methods in Medical Research · doi:10.1177/09622802241269646 · Cited by 18
“In addition, after trimming, we considered two specific strategies: (1) not to re-estimate the PS (for instance, as adopted by Sturmer et al. 8 ) and (2) to re-run the PS model on the trimmed sample and re-estimate PSs, following the recommendation from Li et al. 38 3 Weighted Average Treatment Effect on the Treated”
MethodLiu, F., Yang, W., Yang, W., Xu, R., Chen, L., He, Y., Liu, Z., Zhou, F., Hou, B., Zhang, L., et al. (2021) · Annals of Surgery · doi:10.1097/sla.0000000000005296 · Cited by 18
Rizk, J. G., Wenziger, C. M., Tran, D., Hashemi, L., Moradi, H., Streja, E., & Ahluwalia, A. (2021) · Drugs · doi:10.1007/s40265-021-01639-2 · Cited by 18
“The PS analysis included three models: the first where veterans were matched 1-to-1 on their estimated PS, the second where the PS was included as a variable in model adjustment, and the third method of overlap PS weighting where each veteran weighs equal to the probability of being in the opposite exposure group [32,…”
MethodAdverse events following robotic surgery: population-based analysis
Muaddi, H., Stukel, T. A., de Mestral, C., Nathens, A. B., Pautler, S. E., Shayegan, B., Hanna, W. C., Schlachta, C. M., Breau, R. H., Hopkins, L., et al. (2022) · British journal of surgery · doi:10.1093/bjs/znac119 · Cited by 18
Variance estimation for the average treatment effects on the treated and on the controls
Matsouaka, R., Liu, Y., & Zhou, Y. (2022) · Statistical Methods in Medical Research · doi:10.1177/09622802221142532 · Cited by 18
“Further research is needed to provide threshold-independent estimators similar to the overlap weight estimators.(53) While the wild bootstrap methods to estimate the variance have been investigated proficiently in PS matching,(36) this is the first paper to use such methods in PS weighting.”
MethodGhazi, L., Li, F., Simonov, M., Yamamoto, Y., Nugent, J. T., Greenberg, J. H., Bakhoum, C. Y., Peixoto, A. J., & Wilson, F. P. (2022) · Journal of Hypertension · doi:10.1097/hjh.0000000000003328 · Cited by 18
“converge to zero and all covariates are balanced in the overlap propensity weighted cohort [17,19].”
BackgroundSelf-citationCovariate adjustment in subgroup analyses of randomized clinical trials: A propensity score approach
Yang, S., Li, F., Thomas, L. E., & Li, F. (2021) · Clinical Trials · doi:10.1177/17407745211028588 · Cited by 18
Self-citation
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.