The DOI matches its Crossref record.
Generalized Estimating Equations: Notes on the Choice of the Working Correlation Matrix
Abstract
Summary: Background: Generalized estimating equations (GEE) are an extension of generalized linear models (GLM) in that they allow adjusting for correlations between observations. A major strength of GEE is that they do not require the correct specification of the multivariate distribution but only of the mean structure. Objectives: Several concerns have been raised about the validity of GEE when applied to dichotomous dependent variables. In this contribution, we summarize the theoretical findings concerning efficiency and validity of GEE. Methods: We introduce the GEE in a formal way, summarize general findings on the choice of the working correlation matrix, and show the existence of a dilemma for the optimal choice of the working correlation matrix for dichotomous dependent variables. Results: Biological and statistical arguments for choosing a specific working correlation matrix are given. Three approaches are described for overcoming the range restriction of the correlation coefficient. Conclusions: The three approaches described in this article for overcoming the range restrictions for dichotomous dependent variables in GEE models provide a simple and practical way for use in applications.
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
“When the number of experimental units was small, the GEE1 sandwich estimator of the variance provided standard errors that were too small and therefore inflated the type 1 error rate31,32.”
From A practical solution to pseudoreplication bias in single-cell studies (2021) · cites this paper as [31]
Citations
Cited by
Sorted by citations
Items 101–126 of 126
Ge, X., Peng, Y., & Tu, D. (2022) · Canadian Journal of Statistics · doi:10.1002/cjs.11737 · Cited by 1
Dahdal, J., Bakker, F., Svanerud, J., et al. (2024) · Heart and Vessels · doi:10.1007/s00380-023-02356-4 · Cited by 1
Otsuka, Y., Miyoshi, T., Tanaka, Y., Nakajima, S., & Kaneita, Y. (2025) · Journal of Sleep Research · doi:10.1111/jsr.70101 · Cited by 1
Stannah, J., Knight, J., Sandfort, T. G. M., Laurent, C., Otieno, F., Larmarange, J., Coulaud, P.-J., Mudhune, V., Hamilton, E. L., Cummings, V., et al. (2025) · AIDS and Behavior · doi:10.1007/s10461-025-04799-4 · Cited by 1
Lee, J., Kim, J., & Kim, J. (2025) · Journal of Physical Activity and Health · doi:10.1123/jpah.2025-0011 · Cited by 1
Park, E. H., Choi, S. T., Song, J. S., Kang, E. H., Lee, Y. J., & Ha, Y. (2025) · Seminars in Arthritis and Rheumatism · doi:10.1016/j.semarthrit.2025.152790 · Cited by 1
Brown, U. T., Azogui‐Lévy, S., Nabet, C., Dufourg, M., Charles, M.-A. A., Kerguen, J., Kaminski, M., Marchand‐Martin, L., & Germa, A. (2025) · Community Dentistry And Oral Epidemiology · doi:10.1111/cdoe.70012 · Cited by 1
Determinants of Intergrader Agreement for Key Retinal Photography and OCT Biomarkers in AMD
Trinh, M., Duong, A., Cheung, R., Chen, S. D. M., Ng, D., Friedrich, J., Hodge, C., Nivison‐Smith, L., & Ly, A. (2025) · Translational Vision Science & Technology · doi:10.1167/tvst.14.12.4 · Cited by 1
“Unlike prior reports relying solely on κ statistics or Bland–Altman plots (e.g., for retinal atrophy), 12 we employed generalized estimating equations 24 to model the odds of agreement, accounting for intrapartici-pant correlations and adjusting for key covariates.”
Oli, T. R., Saud, P. S., Blazier, M. A., Yáñez, M. A., & Pelkki, M. H. (2026) · Forest Ecology and Management · doi:10.1016/j.foreco.2025.123491 · Cited by 3
Orudzheva, L., Salimath, M. S., & Pavur, R. (2026) · Journal of Management Control · doi:10.1007/s00187-025-00407-7 · Cited by 1
Zhou, N., Tang, S., Zhou, J., Guo, L., Junlian, L., Situ, B., & Liu, X. (2026) · European Journal of Psychotraumatology · doi:10.1080/20008066.2026.2651656 · Cited by 1
Ameri, N., Arshad, M., Ghaffari, M., et al. (2026) · International Dental Journal · doi:10.1016/j.identj.2026.109553 · Cited by 1
“33 An exchange-able (compound symmetry) correlation structure was assumed to model the correlation among repeated scans within the same cast − scanner combination.”
Zhang, Y., Xie, X., Gong, X., et al. (2026) · Physica Scripta · doi:10.1088/1402-4896/ae8343 · Cited by 1
“Only the coefficient β is eliminated via normalization, yielding [23, 24] (2.5) In the equation, R = ∂ tt only describes the independent evolution in the time dimension.”
InfluentialBaghfalaki, T., Ganjali, M., & Berridge, D. M. (2018) · Journal of the Korean Statistical Society · doi:10.1016/j.jkss.2018.05.001 · Cited by 1
SAGA Application for Generalized Estimating Equations Analysis
Moncaixa, L., & Braga, A. C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-37108-0_4 · Cited by 1
Impacts of informant replacement in two industry‐sponsored Alzheimer's disease clinical trials
Nishida, M. K., Nuño, M. M., Grill, J. D., et al. (2024) · Alzheimer s & Dementia Translational Research & Clinical Interventions · doi:10.1002/trc2.70009 · Cited by 1
Arovah, N. I. (1905) · Queensland University of Technology · doi:10.5204/thesis.eprints.118193
Pregnancies in Lupus: Monitoring and Metrics
Vinet, É., & Ensworth, S. (2021) · Springer eBooks · doi:10.1007/978-3-030-73303-2_9
Kindalova, P., Veldsman, M., Nichols, T. E., & Kosmidis, I. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.11.01.466751
Männistö, S. A., Muotka, J. S., Lappalainen, R. I., Pietiläinen, K. H., & Korpela, R. (2024) · doi:10.2196/preprints.66518
Liu, L., Chen, J., Liang, S., Yang, W., Peng, X., Cai, C., Huang, A., Wang, X., & Zhao, J. (2023) · Figshare · doi:10.6084/m9.figshare.22624132
MEDEIROS, L. E. B. D., Rados, D. R. V., Roman, R., de Oliveira, E. B., Katz, N., Gonçalves, M. R., & Giugliani, C. (2026) · Telemedicine Journal and e-Health · doi:10.1177/15305627251413374
Renda, E., Lamanuzzi, S., & Côté, J. N. (2026) · Journal of Electromyography and Kinesiology · doi:10.1016/j.jelekin.2026.103114
Xie, H., Soh, K. G., Puad, M. H. M., et al. (2025) · International Journal of Education and Training (InjET) · doi:10.47836/injet.11.3.10
Li, R.-D., Reiter, J. L., Wyatt-Johnson, S. K., Dong, C.-P., Smith, C., Green, N., Gao, H.-Y., Hauser, S. R., Kapoor, M., Stevens, J., et al. (2026) · Brain Communications · doi:10.1093/braincomms/fcag264
Mata, F., Cerqueira, J. O. L., Vaz, P. S., Paixão, G., & Araújo, J. P. (2026) · Ruminants · doi:10.3390/ruminants6030065
Metadata
- Authors
- Vens, M., & Ziegler, A.
- Affiliations
- University Hospital Schleswig-Holstein (DE)
- ORCID
- Ziegler, A.
- Venue
- Methods of Information in Medicine
- Publisher
- Georg Thieme Verlag KG
- Published
- 2010
- Volume
- 49
- Issue
- 05
- Pages
- 421-425
- ISSN
- 0026-1270 (ISSN-L)
- 2511-705X
- OpenAlex
- W4292366122
- Cited by
- 127
- References
- 0
- Citations by year
- 2026: 11 · 2025: 13 · 2024: 13 · 2023: 13 · 2022: 8 · 2021: 12 · 2020: 7 · 2019: 5 · 2018: 8 · 2017: 10 · 2016: 6 · 2015: 5 · 2014: 8 · 2013: 5 · 2012: 1
- FWCI
- 1.91
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Methods of Information in Medicine (publishedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Spatial and Panel Data Analysis
- Keywords
- generalized estimating equations, working correlation matrix, dichotomous dependent variable, correlated binary data, estimator efficiency, generalized linear models
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
