{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T11:01:14Z","timestamp":1790420474843,"version":"4.1.0"},"reference-count":30,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Agency for Health Research and Quality","award":["R01 HS027791"],"award-info":[{"award-number":["R01 HS027791"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Generalized estimating equations (GEEs) are widely used for modeling clustered data while accounting for within-cluster correlations. However, fitting GEEs on massive datasets can be computationally prohibitive. Subsampling offers a practical solution, but efficient subsampling strategies for large clustered data, particularly with rare events, remain underexplored. Simple random subsampling can lead to a substantial loss of rare-event information, resulting in inefficient estimation, computational instability, and increased finite-sample bias. Additionally, intra-cluster correlation complicates inference on subsampled data, requiring methods that preserve correlation structure while adjusting for unequal sampling probabilities. To address these challenges, we develop an individual-level sampling scheme and derive optimal subsampling probabilities based on GEEs. We propose a subsampling-based weighted GEE (SaWGEE) estimator that efficiently approximates the full-data GEE estimator and establish its asymptotic properties as the number or size of clusters grows. The optimal subsampling probabilities minimize the asymptotic mean-square-error or its upper bound of the SaWGEE estimator, conditional on observed data, under an independent or exchangeable working correlation structure. Simulation studies evaluate the performance of the SaWGEE estimator against conventional subsampling strategies, such as random or 1:1 case-control sampling, and the standard full-data GEEs when feasible. We apply the proposed method to the 2022 CDC survey data, where observations are clustered by state, to construct a risk-adjustment model for heart attack incidence.<\/jats:p>","DOI":"10.1093\/biomtc\/ujag163","type":"journal-article","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:49:45Z","timestamp":1789040985000},"source":"Crossref","is-referenced-by-count":0,"title":["Optimal subsampling methods for large clustered imbalanced data based on generalized estimating equations"],"prefix":"10.1093","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1628-5819","authenticated-orcid":false,"given":"Tingting","family":"Yu","sequence":"first","affiliation":[{"name":"Department of Population Medicine, Harvard Pilgrim Healthcare Institute and Harvard Medical School , Boston, MA 02215 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sehwan","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Population Medicine, Harvard Pilgrim Healthcare Institute and Harvard Medical School , Boston, MA 02215 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5007-193X","authenticated-orcid":false,"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Population Medicine, Harvard Pilgrim Healthcare Institute and Harvard Medical School , Boston, MA 02215 ,","place":["United States"]},{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health , Boston, MA 02115 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,26]]},"reference":[{"key":"2026092606032803100_bib1","first-page":"749","article-title":"Optimal subsampling algorithms for big data regressions","volume":"31","author":"Ai","year":"2021","journal-title":"Statistica Sinica"},{"key":"2026092606032803100_bib2","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1093\/cid\/ciaa012","article-title":"The limited utility of ranking hospitals based on their colon surgery infection rates","volume":"72","author":"Caroff","year":"2021","journal-title":"Clinical Infectious Diseases"},{"key":"2026092606032803100_bib3","doi-asserted-by":"crossref","first-page":"1260","DOI":"10.1093\/jrsssb\/qkaf017","article-title":"Multi-resolution subsampling for linear classification with massive data","volume":"87","author":"Chen","year":"2025","journal-title":"Journal of the Royal Statistical Society Series B: Statistical Methodology"},{"key":"2026092606032803100_bib4","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1080\/10618600.2019.1710156","article-title":"A stochastic second-order generalized estimating equations approach for estimating association parameters","volume":"29","author":"Chen","year":"2020","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"2026092606032803100_bib5","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1001\/jamacardio.2018.1115","article-title":"Outcomes of care for ischemic heart disease and chronic heart failure in the Veterans Health Administration","volume":"3","author":"Groeneveld","year":"2018","journal-title":"JAMA Cardiology"},{"key":"2026092606032803100_bib6","first-page":"142","article-title":"Optimal subsampling algorithm for the marginal model with large longitudinal data","volume-title":"Statistics and Computing","author":"Han","year":"2026"},{"key":"2026092606032803100_bib7","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1097\/EDE.0000000000000763","article-title":"On the analysis of case-control studies in cluster-correlated data settings","volume":"29","author":"Haneuse","year":"2018","journal-title":"Epidemiology (Cambridge, Mass.)"},{"key":"2026092606032803100_bib8","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1093\/biomet\/88.4.1121","article-title":"Within-cluster resampling","volume":"88","author":"Hoffman","year":"2001","journal-title":"Biometrika"},{"key":"2026092606032803100_bib9","doi-asserted-by":"crossref","first-page":"2262","DOI":"10.1080\/01621459.2023.2209349","article-title":"Analyzing big EHR data - optimal Cox regression subsampling procedure with rare events","volume":"118","author":"Keret","year":"2023","journal-title":"Journal of the American Statistical Association"},{"key":"2026092606032803100_bib10","doi-asserted-by":"crossref","first-page":"1377","DOI":"10.1002\/(SICI)1097-0258(19970630)16:12<1377::AID-SIM557>3.0.CO;2-K","article-title":"Re-using data from case-control studies","volume":"16","author":"Lee","year":"1997","journal-title":"Statistics in Medicine"},{"key":"2026092606032803100_bib11","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1093\/biomet\/73.1.13","article-title":"Longitudinal data analysis using generalized linear models","volume":"73","author":"Liang","year":"1986","journal-title":"Biometrika"},{"key":"2026092606032803100_bib12","doi-asserted-by":"crossref","first-page":"734","DOI":"10.1080\/10618600.2017.1321552","article-title":"One-step generalized estimating equations with large cluster sizes","volume":"26","author":"Lipsitz","year":"2017","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"2026092606032803100_bib13","first-page":"861","article-title":"A statistical perspective on algorithmic leveraging","volume":"16","author":"Ma","year":"2015","journal-title":"The Journal of Machine Learning Research"},{"key":"2026092606032803100_bib14","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1111\/rssa.12503","article-title":"Outcome-dependent sampling in cluster-correlated data settings with application to hospital profiling","volume":"183","author":"McGee","year":"2020","journal-title":"Journal of the Royal Statistical Society Series A: Statistics in Society"},{"key":"2026092606032803100_bib15","doi-asserted-by":"crossref","DOI":"10.1137\/1.9780898719109","volume-title":"Optimal Design of Experiments","author":"Pukelsheim","year":"2006"},{"key":"2026092606032803100_bib16","article-title":"Indicators of Heart disease","author":"Pytlak","year":"2022"},{"key":"2026092606032803100_bib17","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1093\/biomet\/asq078","article-title":"Assessing the validity of weighted generalized estimating equations","volume":"98","author":"Qu","year":"2011","journal-title":"Biometrika"},{"key":"2026092606032803100_bib18","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1017\/ice.2018.310","article-title":"Comparison of hospital surgical site infection rates and rankings using claims versus National Healthcare Safety Network surveillance data","volume":"40","author":"Rhee","year":"2019","journal-title":"Infection Control & Hospital Epidemiology"},{"key":"2026092606032803100_bib19","doi-asserted-by":"crossref","first-page":"4090","DOI":"10.1002\/sim.9016","article-title":"Optimal allocation in stratified cluster-based outcome-dependent sampling designs","volume":"40","author":"Sauer","year":"2021","journal-title":"Statistics in Medicine"},{"key":"2026092606032803100_bib20","doi-asserted-by":"crossref","first-page":"2441","DOI":"10.1002\/sim.4359","article-title":"Outcome-dependent sampling for longitudinal binary response data based on a time-varying auxiliary variable","volume":"31","author":"Schildcrout","year":"2012","journal-title":"Statistics in Medicine"},{"key":"2026092606032803100_bib21","first-page":"93","article-title":"Heart disease and stroke statistics\u20142023 update: A report from the American Heart Association","volume":"147","author":"Tsao","year":"2023","journal-title":"Circulation [Computer File]"},{"key":"2026092606032803100_bib22","doi-asserted-by":"crossref","first-page":"393","DOI":"10.1080\/01621459.2017.1408468","article-title":"Information-based optimal subdata selection for big data linear regression","volume":"114","author":"Wang","year":"2019","journal-title":"Journal of the American Statistical Association"},{"key":"2026092606032803100_bib23","doi-asserted-by":"crossref","first-page":"829","DOI":"10.1080\/01621459.2017.1292914","article-title":"Optimal subsampling for large sample logistic regression","volume":"113","author":"Wang","year":"2018","journal-title":"Journal of the American Statistical Association"},{"key":"2026092606032803100_bib24","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/s11009-023-10015-4","article-title":"Subsampling in longitudinal models","volume":"25","author":"Wang","year":"2023","journal-title":"Methodology and Computing in Applied Probability"},{"key":"2026092606032803100_bib25","doi-asserted-by":"crossref","first-page":"899","DOI":"10.1002\/sim.7543","article-title":"A novel case-control subsampling approach for rapid model exploration of large clustered binary data","volume":"37","author":"Wright","year":"2018","journal-title":"Statistics in Medicine"},{"key":"2026092606032803100_bib26","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1214\/aos\/1046294467","article-title":"Asymptotics for generalized estimating equations with large cluster sizes","volume":"31","author":"Xie","year":"2003","journal-title":"The Annals of Statistics"},{"key":"2026092606032803100_bib27","doi-asserted-by":"crossref","first-page":"467","DOI":"10.1007\/s00362-022-01386-w","article-title":"A review on design inspired subsampling for big data","volume":"65","author":"Yu","year":"2024","journal-title":"Statistical Papers"},{"key":"2026092606032803100_bib28","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1080\/01621459.2020.1773832","article-title":"Optimal distributed subsampling for maximum quasi-likelihood estimators with massive data","volume":"117","author":"Yu","year":"2022","journal-title":"Journal of the American Statistical Association"},{"key":"2026092606032803100_bib29","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1097\/EDE.0b013e31806462d3","article-title":"Outcome-dependent sampling: an efficient sampling and inference procedure for studies with a continuous outcome","volume":"18","author":"Zhou","year":"2007","journal-title":"Epidemiology (Cambridge, Mass.)"},{"key":"2026092606032803100_bib30","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1002\/sim.8783","article-title":"Sampling-based estimation for massive survival data with additive hazards model","volume":"40","author":"Zuo","year":"2021","journal-title":"Statistics in Medicine"}],"container-title":["Biometrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/82\/3\/ujag163\/71401604\/ujag163.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/82\/3\/ujag163\/71401604\/ujag163.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T10:03:38Z","timestamp":1790417018000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biometrics\/article\/doi\/10.1093\/biomtc\/ujag163\/8836500"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":30,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/biomtc\/ujag163","relation":{},"ISSN":["0006-341X","1541-0420"],"issn-type":[{"value":"0006-341X","type":"print"},{"value":"1541-0420","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,7,1]]},"article-number":"ujag163"}}