Some Methods of Propensity‐Score Matching had Superior Performance to Others: Results of an Empirical Investigation and Monte Carlo simulations
The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.
Abstract
Propensity‐score matching is increasingly being used to reduce the impact of treatment‐selection bias when estimating causal treatment effects using observational data. Several propensity‐score matching methods are currently employed in the medical literature: matching on the logit of the propensity score using calipers of width either 0.2 or 0.6 of the standard deviation of the logit of the propensity score; matching on the propensity score using calipers of 0.005, 0.01, 0.02, 0.03, and 0.1; and 5 → 1 digit matching on the propensity score. We conducted empirical investigations and Monte Carlo simulations to investigate the relative performance of these competing methods. Using a large sample of patients hospitalized with a heart attack and with exposure being receipt of a statin prescription at hospital discharge, we found that the 8 different methods produced propensity‐score matched samples in which qualitatively equivalent balance in measured baseline variables was achieved between treated and untreated subjects. Seven of the 8 propensity‐score matched samples resulted in qualitatively similar estimates of the reduction in mortality due to statin exposure. 5 → 1 digit matching resulted in a qualitatively different estimate of relative risk reduction compared to the other 7 methods. Using Monte Carlo simulations, we found that matching using calipers of width of 0.2 of the standard deviation of the logit of the propensity score and the use of calipers of width 0.02 and 0.03 tended to have superior performance for estimating treatment effects (© 2009 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim)
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
“Also, calliper matchings with widths of 0.2, 0.02 and 0.03 have been reported to have superior results [49], which prompted us to use this method.”
Citations
Cites
R: A Language and Environment for Statistical Computing
R Core Team (2025) · doi:10.32614/r.manuals · Cited by 352,181
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
Rosenbaum, P. R., & Rubin, D. B. (1985) · The American Statistician · doi:10.2307/2683903 · Cited by 4,774
Reducing Bias in Observational Studies Using Subclassification on the Propensity Score
Rosenbaum, P. R., & Rubin, D. B. (1984) · Journal of the American Statistical Association · doi:10.1080/01621459.1984.10478078 · Cited by 3,082
A critical appraisal of propensity‐score matching in the medical literature between 1996 and 2003
Austin, P. C. (2008) · Statistics in Medicine · doi:10.1002/sim.3150 · Cited by 1,249
Self-citationAustin, P. C., Grootendorst, P., & Anderson, G. M. (2007) · Statistics in Medicine · doi:10.1002/sim.2580 · Cited by 1,137
Self-citationThe performance of different propensity score methods for estimating marginal hazard ratios
Austin, P. C. (2013) · Statistics in Medicine · doi:10.1002/sim.5705 · Cited by 1,006
Self-citationControlling Bias in Observational Studies: A Review
Cochran, W. G. (2006) · Matched Sampling for Causal Effects · doi:10.1017/cbo9780511810725.005 · Cited by 958
Reducing bias in a propensity score matched-pair sample using greedy matching techniques
Parsons, L. (2001) · Medical Entomology and Zoology · Cited by 733
Austin, P. C. (2007) · The Journal of Thoracic and Cardiovascular Surgery · doi:10.1016/j.jtcvs.2007.07.021 · Cited by 589
Self-citation
Cited by
Items 401–500 of 795
Endocuff Vision improves adenoma detection rate in a large screening-related cohort
Forbes, N., Hilsden, R. J., Ruan, Y., Poirier, A. E., O'Sullivan, D. E., Craig, K. M., Kerrison, D., Brenner, D. R., & Heitman, S. J. (2021) · Endoscopy International Open · doi:10.1055/a-1533-6183 · Cited by 14
“A caliper width of 0.01 without replacement was used for matching and the treatment observations with propensity scores outside the range of the propensity scores of the controls were dropped [29].”
InfluentialMohammad, H. R., Judge, A., & Murray, D. W. (2021) · PubMed · doi:10.2106/jbjs.21.00179 · Cited by 13
Mussa, E. C., Agegnehu, D., & Nshakira‐Rukundo, E. (2024) · PLoS ONE · doi:10.1371/journal.pone.0283812 · Cited by 13
Kibuchi, E., Sturgis, P., Durrant, G. B., & Maslovskaya, O. (2024) · Journal of Survey Statistics and Methodology · doi:10.1093/jssam/smae017 · Cited by 15
“The choice of these caliper widths is based on most used calipers in the PS literature (e.g., Austin 2009b).”
InfluentialParmar, A. D., Sheffield, K. M., Han, Y., Vargas, G., Guturu, P., Kuo, Y., Goodwin, J. S., & Riall, T. S. (2013) · Cancer · doi:10.1002/cncr.28295 · Cited by 13
“Patients who received an EUS were matched based on propensity score to patients who did not receive an EUS by 1:1, 1:2, and 1:3 matching, using the Greedy matching technique.(15) Figure 1 shows the overlap in propensity scores for patients who did and did not receive EUS; only overlapping patients were included for an…”
MethodChoi, M. Y., Li, D., Feldman, C. H., Yoshida, K., Guan, H., Kim, S. C., Everett, B. M., & Costenbader, K. H. (2020) · Rheumatology · doi:10.1093/rheumatology/keaa862 · Cited by 14
Basic Needs Insecurity and College Students’ Mental Health During the COVID-19 Pandemic
Soria, K. M. (2023) · Journal of Postsecondary Student Success · doi:10.33009/fsop_jpss130999 · Cited by 14
Lipoprotein(a): A Residual Cardiovascular Risk Factor in Statin-Treated Stroke Survivors
Chemello, K., Gallo, A., Guédon, A. F., Techer, R., Croyal, M., Swietek, M. J., Meilhac, O., Amarenco, P., & Lambert, G. C. (2023) · JACC Advances · doi:10.1016/j.jacadv.2023.100557 · Cited by 13
Management of Abdominal Drainage after Hepatic Resection
Inoue, Y. H., Imai, Y., Kawaguchi, N., Hirokawa, F., Hayashi, M., & Uchiyama, K. (2017) · Digestive Surgery · doi:10.1159/000455238 · Cited by 13
Zhang, F., Ma, B., Huang, Y.-Y., Chen, W., Chen, J., Dong, Q., Chen, W., Chen, X.-L., Shen, X., Yu, Z., et al. (2019) · Surgical Endoscopy · doi:10.1007/s00464-019-07249-0 · Cited by 13
Zhao, E., Zhou, C., & Chen, S. (2019) · Future Oncology · doi:10.2217/fon-2019-0473 · Cited by 13
Comparative effectiveness of dimethyl fumarate in multiple sclerosis
Bosco‐Lévy, P., Debouverie, M., Brochet, B., Guillemin, F., Louapre, C., Maillart, É., Heinzlef, O., Lignot, S., Diez, P., Abouelfath, A., et al. (2021) · British Journal of Clinical Pharmacology · doi:10.1111/bcp.15071 · Cited by 13
“The analysis of an hdPS matched sample can mimic that of an RCT: one can directly compare outcomes between treated and untreated subjects within the matched sample.(32) Unlike covariate adjustment using the propensity score, propensity score matching does not require that an outcomes model be specified.”
ResultAssociation Between Fetal Safety Outcomes and Exposure to Local Podophyllotoxin During Pregnancy
Andersson, N. W., & Andersen, J. T. (2020) · JAMA Dermatology · doi:10.1001/jamadermatol.2019.4315 · Cited by 13
Does Levosimendan hasten veno-arterial ECMO weaning? A propensity score matching analysis
Paulo, N., Kimmoun, A., Hajage, D., Hubert, P., Levy, D., de Chambrun, M. P., Chommeloux, J., Saura, O., Marmol, G. D., Moyon, Q., et al. (2025) · Annals of Intensive Care · doi:10.1186/s13613-025-01457-9 · Cited by 12
“Patients were matched on the specified variables and using a 1:1 propensity score matching procedure without replacement, with a caliper width of 0.1, resulting in minimal differences between matched variables as recommended [25].”
InfluentialSharma, V., Sonkar, S. C., Singhal, P., Kumar, A., Singh, R. K., Ramachandran, V. G., Hariprasad, R., Saluja, D., & Bharadwaj, M. (2021) · Scientific Reports · doi:10.1038/s41598-020-79963-y · Cited by 12
Zhou, Y., Ye, S., Yang, C.-Z., Gao, R., Ming, A., Diao, M., & Li, L. (2022) · Journal of Pediatric Surgery · doi:10.1016/j.jpedsurg.2022.01.018 · Cited by 12
Maldonado, D. R., Ouyang, V. W., Lee, M. S., Jimenez, A. E., Sabetian, P. W., Saks, B. R., Lall, A. C., & Domb, B. G. (2022) · Arthroscopy The Journal of Arthroscopic and Related Surgery · doi:10.1016/j.arthro.2022.02.005 · Cited by 12
Owens, J. S., Jimenez, A. E., Lee, M. S., Hawkins, G. C., Maldonado, D. R., & Domb, B. G. (2022) · The American Journal of Sports Medicine · doi:10.1177/03635465221092762 · Cited by 13
“Previous studies have shown that the optimal method to detect potential differences between 2 groups is greedy matching without replacement.(1,4,5) Basketball and cutting sports athletes were matched using a caliper of 0.”
MethodChung, K., Juang, S., Chen, H., Cheng, K., Wu, K., Song, L., & Lee, K. (2022) · BMC Gastroenterology · doi:10.1186/s12876-022-02505-5 · Cited by 12
Weng, C.-F., Wu, C., Wu, M.-H., & Lin, F. (2022) · CHEST Journal · doi:10.1016/j.chest.2022.11.027 · Cited by 12
Zhong, Q., Tang, Y.-H., Liu, Z.-Y., Zhang, Z.-Q., He, Q.-C., Li, P., Xie, J., Wang, J., Lin, J., Lü, J., et al. (2024) · International Journal of Surgery · doi:10.1097/js9.0000000000001325 · Cited by 12
“The cut-off for the absolute standardized mean difference, which indicated a signi fi cant imbalance, was set at 0.100 [21] .”
InfluentialDesai, R. J., Bradley, M. C., Lee, H., Eworuke, E., Weberpals, J. G., Wyss, R., Schneeweiß, S., & Ball, R. (2024) · American Journal of Epidemiology · doi:10.1093/aje/kwae102 · Cited by 14
Scarcia, L., Colò, F., Alexandre, A. M., Brunetti, V., Pedicelli, A., Arba, F., Ruggiero, M., Piano, M., Gabrieli, J. D., Ros, V. D., et al. (2024) · American Journal of Neuroradiology · doi:10.3174/ajnr.a8421 · Cited by 12
Mak, L., Hui, R. W., Chung, M. S. H., Wong, D. K.-H., Fung, J., Seto, W., & Yuen, M. (2024) · Journal of Gastroenterology and Hepatology · doi:10.1111/jgh.16728 · Cited by 12
Gayat, É., Thabut, G., Christie, J. D., Mebazaa, A., Mary, J., & Porcher, R. (2013) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2013.03.018 · Cited by 12
“20 standard deviations of the logit of the estimated PS, because this method has been reported to provide a good treatment-effect estimate in terms of mean squared errors (MSEs) [6].”
MethodInfluentialLeiber, M. J., Fox, B., Escue, M., Krupa, J. M., & Cochran, J. K. (2020) · Justice Quarterly · doi:10.1080/07418825.2020.1781232 · Cited by 12
“05 caliper was used to optimize the ability to exclude bad matches, while simultaneously increasing the potential for good matches to occur (Austin, 2009; Rosenbaum, 2002).”
BackgroundMethodInfluentialJimenez, A. E., Monahan, P. F., Owens, J. S., Maldonado, D. R., Curley, A. J., & Domb, B. G. (2021) · Arthroscopy The Journal of Arthroscopic and Related Surgery · doi:10.1016/j.arthro.2021.11.053 · Cited by 12
Zhang, X., Wang, L., & Zhang, X. (2014) · BMC Health Services Research · doi:10.1186/s12913-014-0492-6 · Cited by 12
“03 [14], and caliper matching with one-to-one matches based on the propensity scores was used in this study.”
MethodBäumler, M., Stargardt, T., Schreyögg, J., & Busse, R. (2012) · Applied Health Economics and Health Policy · doi:10.2165/11597340-000000000-00000 · Cited by 12
An Association Between Hyperchloremia and Acute Kidney Injury in Patients With Acute Ischemic Stroke
Haller, J. T., Smetana, K. S., Erdman, M. J., Miano, T. A., Riha, H. M., Rinaldi, A., Goyal, N., & Jones, G. M. (2020) · The Neurohospitalist · doi:10.1177/1941874420913715 · Cited by 12
“2 standard deviations of the propensity score.(22) In the matched sample, the association between moderate hyperchloremia and AKI was examined with a modified Poisson regression model.”
MethodMurata, S., Tsutsui, S., Hashizume, H., Minamide, A., Nakagawa, Y., Iwasaki, H., Takami, M., Nagata, K., Murakami, K., Taiji, R., et al. (2022) · European Spine Journal · doi:10.1007/s00586-022-07379-5 · Cited by 11
“2 standard deviations of the logit of the propensity score [18].”
BackgroundCampbell, C. M., & Labrecque, R. M. (2022) · Journal of Experimental Criminology · doi:10.1007/s11292-022-09532-y · Cited by 11
“Some scholars have attempted to address these situational components when it comes to estimating differences that may be sensitive in the modeling process (e.g., Austin, 2009, 2010; Hill, 2008).”
A Comparison of the Periprosthetic Fracture Rate of Unicompartmental and Total Knee Replacements
Mohammad, H. R., Barker, K. L., Judge, A., & Murray, D. W. (2023) · Journal of Bone and Joint Surgery · doi:10.2106/jbjs.22.01302 · Cited by 11
“This approach has been shown to have superior performance for estimating treatment effects 32 .”
BackgroundValente, I., Alexandre, A. M., Colò, F., Brunetti, V., Frisullo, G., Camilli, A., Falcou, A., Scarcia, L., Gigli, R., Scala, I., et al. (2023) · World Neurosurgery · doi:10.1016/j.wneu.2023.12.117 · Cited by 11
“24 To determine the effect of anesthesia, coef fi cients were calculated for each of the clinical and procedural outcome measures with logistic regression and ordinal logistic regression.”
Chen, Y., Lin, Y., Lu, H., Wu, X., Pan, Y. H., Xia, A., Pang, L., Ye, W., & Xu, F. (2024) · Diagnostic Microbiology and Infectious Disease · doi:10.1016/j.diagmicrobio.2024.116353 · Cited by 12
The role of forgiveness and gratitude in the quality of life of alcohol-dependent persons
Charzyńska, E., Gruszczyńska, E., & Heszen-Celińska, I. (2019) · Addiction Research & Theory · doi:10.1080/16066359.2019.1642332 · Cited by 13
“Next, we conducted 1:1 nearest neighbor propensity score matching, without replacement, and with exact restrictions on gender (Austin 2009).”
BackgroundMethodResultInfluentialMonahan, P. F., Jimenez, A. E., Owens, J. S., Saks, B. R., Maldonado, D. R., Ankem, H. K., Sabetian, P. W., Lall, A. C., & Domb, B. G. (2021) · The American Journal of Sports Medicine · doi:10.1177/03635465211041760 · Cited by 11
Jimenez, A. E., Owens, J. S., Monahan, P. F., Maldonado, D. R., Saks, B. R., Sabetian, P. W., Ankem, H. K., Lall, A. C., & Domb, B. G. (2021) · The American Journal of Sports Medicine · doi:10.1177/03635465211056964 · Cited by 11
Ashkenazi, I., Lawrence, K. W., Thomas, J., Marwin, S. E., Rozell, J. C., & Schwarzkopf, R. M. (2023) · The Journal of Arthroplasty · doi:10.1016/j.arth.2023.04.051 · Cited by 11
Estimation of conditional and marginal odds ratios using the prognostic score
Hajage, D., Rycke, Y. D., Chauvet, G., & Tubach, F. (2016) · Statistics in Medicine · doi:10.1002/sim.7170 · Cited by 12
“For the second step, four methods have been described to account for the estimated PPS in estimating the treatment effect: adjustment on the PPS [5], stratification on the PPS [21, 22], matching on the PPS [4, 23, 24], and weighting using the PPS [25, 26].”
MethodHwang, M.-C. (2016) · Journal of Social Service Research · doi:10.1080/01488376.2016.1216917 · Cited by 11
“Although the value of 0.02 or 0.03 was appropriate for the best matching (Austin, 2009), the value of 0.01 is used as the value of caliper to give more restrictive conditions for exact matching in this article.”
MethodInfluentialOkubo, S., Gotohda, N., Sugimoto, M., Nomura, S., Kobayashi, S., Takahashi, S., Hayashi, R., & Konishi, M. (2018) · Surgery · doi:10.1016/j.surg.2018.04.002 · Cited by 11
Prabhavalkar, O. N., Carbone, A. D., Curley, A. J., Padmanabhan, S., Nerys-Figueroa, J., & Domb, B. G. (2023) · The American Journal of Sports Medicine · doi:10.1177/03635465231204314 · Cited by 10
Frankenstein, L., Katus, H. A., Grundtvig, M., Hole, T., Blois, J. D., Schellberg, D., Atar, D., Zugck, C., & Agewall, S. (2013) · European Journal of Clinical Pharmacology · doi:10.1007/s00228-013-1512-x · Cited by 10
“2 of the standard deviation of the total sample [13].”
BackgroundJimenez, A. E., Monahan, P. F., Owens, J. S., Maldonado, D. R., Saks, B. R., Ankem, H. K., Sabetian, P. W., Lall, A. C., & Domb, B. G. (2021) · The American Journal of Sports Medicine · doi:10.1177/03635465211055175 · Cited by 10
Mohammad, H. R., Judge, A., & Murray, D. W. (2024) · The Journal of Arthroplasty · doi:10.1016/j.arth.2024.02.019 · Cited by 10
Zwolle Myocardial Infarction Study Group, Kilic, S., Hermanides, R. S., Ottervanger, J. P., Kolkman, E., Dambrink, J. H. E., Roolvink, V., Gosselink, A. T. M., Kedhi, E., & Hof, A. W. J. V. ’. (2016) · Netherlands Heart Journal · doi:10.1007/s12471-016-0887-6 · Cited by 10
“Because the patients were not randomly assigned to undergo transradial intervention, a propensity score analysis was performed by using a logistic regression model for transradial versus transfemoral intervention to adjust for differences in baseline characteristics [15].”
MethodAgogo, G. O., Murphy, T. E., McAvay, G., & Allore, H. G. (2019) · Annals of Epidemiology · doi:10.1016/j.annepidem.2019.04.008 · Cited by 10
“The SD for these covariates are greater than a threshold value one for covariance imbalance (19), prompting a need for a statistical technique to correct for the imbalance.”
BackgroundFan, Y., Liu, M., Li, S., Yu, J., Qi, X., Tan, F., Xu, K., Zhang, N., Yao, Z., Yang, H., et al. (2021) · Journal of Cancer Research and Clinical Oncology · doi:10.1007/s00432-020-03503-4 · Cited by 10
“Then, patients undergoing LATG or OTG were paired by a 1:1 nearest available score matching algorithm with a caliper width of 0.02 (Austin 2009; Ralph 1998; Rosenbaum 1983).”
MethodInfluentialWei, Y., Wong, S. K., Wu, T., Law, B. T. T., Ng, E. K., Lam, C. L. K., & Wong, C. K. H. (2021) · Journal of Diabetes · doi:10.1111/1753-0407.13179 · Cited by 10
“2 implied an optimal balance between the groups.(24) Patients with the lowest and highest 1% propensity scores in each group were removed to trim extreme weights in the trimming process.”
BackgroundJohnsen, S. P., Rasmussen, T. B., Falstie‐Jensen, A. M., Harboe, L., Stynes, G., Dybro, L., Hansen, M. L., Brandes, A., Grove, E. L., & Münster, A. B. (2021) · Basic & Clinical Pharmacology & Toxicology · doi:10.1111/bcpt.13625 · Cited by 10
“To assess the positivity assumption (that any patient must have a non-zero probability of getting either treatment), we looked at the estimated weights.(22,23) The mean weight was approximately 1 in all analyses, and none of the individual weights were considered extreme (minimum weight of 0.”
BackgroundSong, X., Li, Q., Diao, J., Li, J., Li, Y., Zhang, S., Chen, L., Wei, J., Shu, J., Liu, Y., et al. (2022) · Frontiers in Pediatrics · doi:10.3389/fped.2022.803568 · Cited by 10
Transition of cooking fuel types and mortality risk in China, 1991–2015
Pu, F., Li, C., Zhang, X., Cao, X., Yang, Z., Hu, Y., Xu, X., Ma, Y., Hu, K., & Liu, Z. (2023) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2023.161654 · Cited by 11
Pirracchio, R., Resche‐Rigon, M., Mebazaa, A., Zannad, F. M., Alla, F., & Chevret, S. (2013) · Journal of Cardiac Failure · doi:10.1016/j.cardfail.2012.12.006 · Cited by 10
Liu, T., Zhao, Z., Wang, J., Chen, X., Huang, J., Jiang, W., Yu, Y.-H., Zhu, X., Wang, R. C., Lin, K. C., et al. (2025) · The Lancet Regional Health - Western Pacific · doi:10.1016/j.lanwpc.2025.101688 · Cited by 9
“24 PSM was conducted using known or suspected confounders associated with outcomes, as well as variables that exhibited significant baseline imbalances between the treatment groups.”
Increased Postoperative Complications in Nontobacco Nicotine Users Following Total Hip Arthroplasty
Fuller, Z., Chopra, A. A., Thomas, J., Oliver, D., Fisher, M., & Abdo, Z. E. (2025) · The Journal of Arthroplasty · doi:10.1016/j.arth.2025.10.032 · Cited by 9
Hashimoto, Y., Hayashi, A., Teng, L., & Igarashi, A. (2021) · Journal of Palliative Medicine · doi:10.1089/jpm.2020.0649 · Cited by 9
“30 Standardized differences were assessed for balance in the baseline characteristics of treatment groups after matching.”
The Effect of the Dwelling Environment on Rural Elderly Cognition: Empirical Evidence from China
Gao, Y., Wang, Y., & Rao, T. (2022) · Sustainability · doi:10.3390/su142416387 · Cited by 9
Qiu, W., Liu, J., He, K., Hu, G., Mei, S., Guan, X., Wang, X., Tian, J., & Tang, J. (2024) · Surgical Endoscopy · doi:10.1007/s00464-024-11085-2 · Cited by 9
“A greedy matching algorithm was used with a caliper width equal to 0.20 of the standard deviation of the log-transformed estimated propensity score (EPS) [16].”
InfluentialWong, C., Ho, I., Choo, A., Lau, R., Fung, T., Chiu, A. C. H.-O., Lam, T.-H., Lin, M., Leung, R. W.-H., Tam, F. C.-C., et al. (2025) · Cardio-Oncology · doi:10.1186/s40959-024-00294-2 · Cited by 9
“A standardized mean difference of ≤0.1 following propensity score matching was considered significantly balanced [12].”
InfluentialLiu, K. S., Wang, B., Mak, I. L., Choi, E. P. H., Lam, C. L. K., & Wan, E. Y. F. (2025) · Hypertension Research · doi:10.1038/s41440-025-02188-x · Cited by 9
“An SMD of less than 0.2 indicates suf fi cient balance [29].”
InfluentialKotz, D., Simpson, C. R., Viechtbauer, W., van Schayck, O. C. P., West, R., & Sheikh, A. (2014) · BMJ Open · doi:10.1136/bmjopen-2014-005281 · Cited by 10
Washam, J. B., Kaltenbach, L. A., WOJDYLA, D. M., Patel, M. R., Klein, A. J. P., Abbott, J. D., & Rao, S. V. (2018) · Circulation Cardiovascular Interventions · doi:10.1161/circinterventions.117.005628 · Cited by 9
Wu, Q., Tang, A.-J., Zeng, L., Niu, S., Tian, M., Jin, A., Yang, H., Chen, J.-J., Xiao-ping, Z., & Shi, Y. (2020) · Journal of Stroke and Cerebrovascular Diseases · doi:10.1016/j.jstrokecerebrovasdis.2020.105437 · Cited by 10
Ankem, H. K., Diulus, S. C., Kyin, C., Jimenez, A. E., Maldonado, D. R., Sabetian, P. W., Saks, B. R., Lall, A. C., & Domb, B. G. (2021) · JAAOS Global Research and Reviews · doi:10.5435/jaaosglobal-d-21-00107 · Cited by 9
Cheng, H., Wang, Z., Gu, W., Yang, X., Song, S., Huang, T., & Lyu, J. (2022) · Clinical Interventions in Aging · doi:10.2147/cia.s387148 · Cited by 9
“1 indicating an imbalance.(30) Kaplan-Meier (KM) survival analysis and Cox proportional-hazards regression models were used to compare the correlations between 30- and 90-day mortality rates in the two patient groups.”
MethodMohammad, H. R., Judge, A., & Murray, D. W. (2023) · Journal of Bone and Joint Surgery · doi:10.2106/jbjs.22.01042 · Cited by 9
Søgaard, M., Skjøth, F., Kjældgaard, J. N., Lip, G. Y. H., & Larsen, T. B. (2017) · Journal of the American Heart Association · doi:10.1161/jaha.117.007453 · Cited by 9
Chan, B., Cadarette, S. M., Wodchis, W. P., Mittmann, N., & Krahn, M. D. (2018) · Wound Medicine · doi:10.1016/j.wndm.2018.01.002 · Cited by 9
Desai, R. J., Wyss, R., Jin, Y., Bohn, J. M., Toh, S., Cosgrove, A., Kennedy, A., Kim, J., Kim, C. T., Ouellet‐Hellstrom, R., et al. (2018) · American Journal of Epidemiology · doi:10.1093/aje/kwy130 · Cited by 9
Yamamoto, M., Asakuma, M., Tanaka, K., Masubuchi, S., Ishii, M., Osumi, W., Hamamoto, H., Okuda, J., & Uchiyama, K. (2019) · Surgical Endoscopy · doi:10.1007/s00464-018-06647-0 · Cited by 9
Mohammad, H. R., Judge, A., & Murray, D. W. (2021) · Acta Orthopaedica · doi:10.2340/17453674.2021.896 · Cited by 9
“Greedy matching without replacement was used given that it has superior performance for estimating treatment effects (22).”
MethodInfluentialTao, S., Ning, M., Lu, Y., Hu, C., Chen, L., & Yang, Y. (2023) · International Journal of Gynecology & Obstetrics · doi:10.1002/ijgo.15011 · Cited by 9
McClish, D. K., Carcaise-Edinboro, P., Esinhart, H. S., Wilson, D., & Bean, M. K. (2014) · Journal of Nutrition Education and Behavior · doi:10.1016/j.jneb.2014.02.015 · Cited by 9
Pirracchio, R., Sprung, C. L., Payen, D. M., & Chevret, S. (2011) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2011.02.009 · Cited by 9
“We first avoided any replacement in matching, as previously recommended [37].”
MethodLima, F. V., Yen, T. Y. M., Butler, J., Yang, J., Xu, J., & Gruberg, L. (2016) · Cardiovascular revascularization medicine · doi:10.1016/j.carrev.2016.08.014 · Cited by 9
Miano, T. A., Yang, W. P., Shashaty, M. G. S., Zuppa, A. F., Brown, J. R., & Hennessy, S. (2020) · Clinical Pharmacology & Therapeutics · doi:10.1002/cpt.1819 · Cited by 12
How Does Transportation Affordability Vary Among TODs, TADs, and Other Areas
Scheer, B. C., Ewing, R., Park, K., & Khan, S. S. A. (2017) · doi:10.15760/trec.181 · Cited by 9
Ashkenazi, I., Rajahraman, V., Lawrence, K. W., Lajam, C. M., Bosco, J. A., & Schwarzkopf, R. M. (2024) · The Journal of Arthroplasty · doi:10.1016/j.arth.2024.01.026 · Cited by 8
Lui, D. T. W., Xiong, X., Cheung, C., Lai, F. T. T., Lai, F. T. T., Fai, W. E. Y., Chui, C. S. L., Chan, E. W., Cheng, F. W. T., Li, L., et al. (2024) · Endocrine Practice · doi:10.1016/j.eprac.2024.03.389 · Cited by 8
Piovan, G., Berardinis, L. D., Screpis, D., Senarighi, M., Povegliano, L., Natali, S., Gigante, A. P., & Zorzi, C. (2024) · Journal of Orthopaedics and Traumatology · doi:10.1186/s10195-024-00765-3 · Cited by 8
“This technique, regarded as an optimal method to evaluate differences between treatment groups, was applied to mitigate the impact of potential confounding variables [59].”
MethodAronow, H. D., Gurm, H. S., Blankenship, J. C., Czeisler, C. A., Wang, T. Y., McCoy, L. A., Neely, M. L., & Spertus, J. A. (2015) · JACC: Cardiovascular Interventions · doi:10.1016/j.jcin.2014.08.010 · Cited by 8
“This approach results in estimates of the treatment effect with lower mean squared error (13).”
BackgroundThe impact of complications after elective colorectal resection within an enhanced recovery pathway
Lee, L., Liberman, S. A., Charlebois, P., Stein, B., Kaneva, P. A., Carli, F., & Feldman, L. S. (2018) · Techniques in Coloproctology · doi:10.1007/s10151-018-1761-x · Cited by 8
“2 of the standard deviation of the logit of the propensity score [11, 12].”
BackgroundEvaluation of Subset Matching Methods: Evidence from a Monte Carlo Simulation Study
Amusa, L. B., Zewotir, T. T., & North, D. (2019) · American Journal of Applied Sciences · doi:10.3844/ajassp.2019.92.100 · Cited by 8
“In the case of greedy matching, a treated unit is chosen randomly, and the nearest control unit is then selected for matching to this treated unit (Austin, 2009).”
BackgroundNair, S. M., Warner, A., Lavi, A., Rodrigues, G., & Chin, J. (2020) · Canadian Urological Association Journal · doi:10.5489/cuaj.6676 · Cited by 8
Solomon, D. H., Ruppert, K. M., Habel, L. A., Finkelstein, J. S., Lian, P., Joffe, H., & Kravitz, H. M. (2021) · BMJ Open · doi:10.1136/bmjopen-2020-045074 · Cited by 8
Padilla, D. E. L., Tinedo, J. R. T., Lajas, A. C., García, L. R., Castillejo, E. O., López-Martín, S., Díaz-Cambriles, T., Virseda, S. G., Melgar, B. A., Pizarro, A. C., et al. (2021) · Journal of Clinical Sleep Medicine · doi:10.5664/jcsm.9656 · Cited by 8
“One-to-one matching without replacement was performed with a 0.2 caliper width, 31,32 and the resulting score-matched pairs were used in subsequent analyses.”
InfluentialManzi, J. E., Kunze, K. N., Meza, B. C., Trauger, N., Quan, T., Rauck, R. C., Carr, J. B., & Dines, J. S. (2021) · Arthroscopy The Journal of Arthroscopic and Related Surgery · doi:10.1016/j.arthro.2021.11.009 · Cited by 8
Kamigaichi, A., Aokage, K., Ikeno, T., Wakabayashi, M., Miyoshi, T., Tane, K., Samejima, J., & Tsuboi, M. (2023) · European Journal of Cardio-Thoracic Surgery · doi:10.1093/ejcts/ezad016 · Cited by 8
Khan, S. A., Ahmed, F. A., Hafeez, M. S., Feng, L. R., Seth, A., Kwon, Y., & Aziz, H. (2023) · Journal of Surgical Oncology · doi:10.1002/jso.27430 · Cited by 8
Ganguli, A. X., Wang, J., & Gourley, D. R. (2011) · Research in Social and Administrative Pharmacy · doi:10.1016/j.sapharm.2010.12.004 · Cited by 8
Bodmann, K. ‐., Schenker, M., Heinlein, W., & Wilke, M. H. (2016) · Medizinische Klinik - Intensivmedizin und Notfallmedizin · doi:10.1007/s00063-016-0183-7 · Cited by 8
Krug, G. (2017) · AStA Wirtschafts- und Sozialstatistisches Archiv · doi:10.1007/s11943-017-0212-x · Cited by 8
“In addition, Austin (2009) found that propensity score matching outperforms propensity score stratification in terms of producing a balance between treatment and control groups.”
BackgroundIglesias, D. G. (2022) · Mathematics · doi:10.3390/math10091547 · Cited by 8
Mendez, L. C., Martell, K., Warner, A., Tseng, C., Chung, H. T.-K., Loblaw, A., Rodrigues, G., & Morton, G. (2020) · Radiotherapy and Oncology · doi:10.1016/j.radonc.2020.06.039 · Cited by 8
Hua, D. Y.-H., Lees, R., Brosnan, M., & Freeman, T. P. (2021) · BMJ Open · doi:10.1136/bmjopen-2021-053814 · Cited by 10
“38 39 Several authors have noted matching with or without replacement is generally comparable, and, indeed, this produced the same sample size in the current study.”
Owens, J. S., Lee, M. S., Jimenez, A. E., Maldonado, D. R., Paraschos, O. A., & Domb, B. G. (2022) · Orthopaedic Journal of Sports Medicine · doi:10.1177/23259671221100861 · Cited by 8
“Previous studies have shown that the optimal method for group comparison is greedy matching without replacement.(2,6,7) A caliper of 0.”
MethodCost-effectiveness of a nurse-delivered, inpatient smoking cessation intervention
Ward, C. E., Hall, S. V., Barnett, P. G., Jordan, N., & Duffy, S. A. (2019) · Translational Behavioral Medicine · doi:10.1093/tbm/ibz101 · Cited by 8
ESG as a turnaround strategy: Evidence from global firms facing performance shortfalls
Kwong, R., Wong, H. S.-M., & Kwok, M. L. J. (2026) · Research in International Business and Finance · doi:10.1016/j.ribaf.2026.103308 · Cited by 8
Calderón‐Parra, J., Grillo, S., Muñóz, P., Machado-Vílchez, M., Delgado-Montero, A., de Alarcón, A., Borrego, M. P., Goenaga-Sánchez, M. Á., Fariñas, M. C., Miró, J. M., et al. (2024) · Journal of Infection · doi:10.1016/j.jinf.2024.106352 · Cited by 7
Metadata
- Authors
- Austin, P. C.
- Affiliations
- University of Toronto (CA)
- Corresponding author
- Austin, Peter C.
- ORCID
- Austin, Peter C.
- Venue
- Biometrical Journal
- Publisher
- Wiley
- Published
- 2009-02
- Volume
- 51
- Issue
- 1
- Pages
- 171-184
- ISSN
- 0323-3847 (ISSN-L)
- 1521-4036
- OpenAlex
- W2016403661
- Cited by
- 769
- References
- 42
- Citations by year
- 2026: 29 · 2025: 50 · 2024: 54 · 2023: 61 · 2022: 78 · 2021: 72 · 2020: 62 · 2019: 48 · 2018: 53 · 2017: 42 · 2016: 48 · 2015: 34 · 2014: 40 · 2013: 33 · 2012: 35
- FWCI
- 18.03
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Biometrical Journal (publishedVersion)
- PubMed (publishedVersion)
- 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, treatment selection bias, observational data, statin exposure, myocardial infarction, mortality reduction, method comparison
- MeSH terms
- Algorithms, Biometry, Canada, Data Interpretation, Statistical, Humans, Monte Carlo Method, Myocardial Infarction, Bias, Confounding Factors, Epidemiologic, Incidence, Survival Rate, Proportional Hazards Models, Survival Analysis, Hydroxymethylglutaryl-CoA Reductase Inhibitors, Prescriptions
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.