A scoping review identified additional considerations for defining estimands in cluster randomised trials

A scoping review identified additional considerations for defining estimands in cluster randomised trials | medRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-P4HH5NV'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search A scoping review identified additional considerations for defining estimands in cluster randomised trials View ORCID Profile Dongquan Bi , View ORCID Profile Andrew Copas , Fan Li , View ORCID Profile Brennan C Kahan doi: https://doi.org/10.1101/2025.06.25.25330127 Dongquan Bi 1 MRC Clinical Trials Unit at UCL, Institute of Clinical Trials and Methodology, University College London , London, UK Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Dongquan Bi Andrew Copas 1 MRC Clinical Trials Unit at UCL, Institute of Clinical Trials and Methodology, University College London , London, UK Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Andrew Copas Fan Li 2 Department of Biostatistics, Yale School of Public Health , New Haven, CT, USA 3 Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine , New Haven, CT, USA 4 Center for Methods in Implementation and Prevention Science, Yale School of Public Health , New Haven, CT, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Brennan C Kahan 1 MRC Clinical Trials Unit at UCL, Institute of Clinical Trials and Methodology, University College London , London, UK Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Brennan C Kahan For correspondence: b.kahan{at}ucl.ac.uk Abstract Full Text Info/History Metrics Supplementary material Data/Code Preview PDF Abstract Background and objective An estimand is a clear description of the treatment effect a study aims to quantify. The ICH E9(R1) addendum lists five attributes that should be described when defining an estimand. However, the addendum was primarily developed for individually randomised trials. Cluster randomised trials (CRTs), in which groups of individuals are randomised, have additional considerations for defining estimands, such as how individuals and clusters are weighted. We aimed to identify a list of additional items that may need to be considered when defining estimands in CRTs. Study design We conducted a systematic search of multiple databases as well as the authors’ personal libraries to identify articles that described an aspect of an estimand definition for CRTs which was not explicitly covered by one of the five attributes listed in the ICH E9 (R1) addendum. From this, we generated a list of items that may require consideration when defining estimands for CRTs beyond the five attributes listed in the ICH E9(R1) addendum. Results From 46 eligible articles, we identified 8 items that may need to be considered when defining estimands in CRTs: (i) population of clusters; (ii) population of individuals under selection bias; (iii) exposure time of individuals/clusters on treatment; (iv) how individuals and clusters are weighted (e.g. individual-average vs. cluster-average); (v) whether summary measures are marginal or cluster-specific; (vi) strategies used to handle cluster-level intercurrent events; (vii) how interference/spillover is handled; and (viii) how individuals who leave or change clusters are handled. Conclusion This review has identified additional items that may need to be considered when defining estimands for CRTs. Study investigators undertaking CRTs should consider these items when defining estimands for their trials, to ensure estimands are unambiguous and relevant for end-users such as clinicians, patients, and policy makers. Key findings The review identified eight additional items that are not explicitly described by the existing attributes listed in the ICH E9(R1) addendum, but that may need to be considered when defining estimands for cluster randomised trials What this adds to what is known Defining estimands using the attributes set out in the ICH E9(R1) addendum can promote clarity, however these attributes alone are not sufficient to describe a clearly defined research question in cluster randomised trials In addition to the five attributes set out in ICH E9(R1), investigators conducting cluster randomised trials need to consider which additional items are relevant to describe when defining their estimand What is the implication and what should we change now Items identified in this review can be used by investigators conducting cluster randomised trials to help define their estimand to ensure it is clear Specific guidance on defining estimands for cluster randomised trials is required to ensure that research questions are fully described in these trials 1. Introduction An estimand is a clear description of the treatment effect a trial aims to quantify [ 1 , 2 ]. The use of estimands can help to clarify the question being investigated and ensure statistical methods are well-aligned to the research question. In 2019, the International Council for Harmonisation published the ICH E9(R1) addendum [ 1 ], which sets out a framework for defining an estimand. This involves specifying five attributes: (1) population of patients; (2) treatment conditions being compared; (3) endpoint/outcome variable; (4) population-level summary measure; and (5) strategies used to handle intercurrent events (post-randomisation events that affect interpretation or existence of the endpoint). [ 1 ] The ICH E9 (R1) addendum was developed by regulators and the pharmaceutical industry, primarily with individually randomised trials in mind. Although the five attributes defined within the addendum will be relevant for all study designs, some designs may require specification of additional considerations in order to have a well-defined estimand. For example, cluster randomised trials (CRTs) involve randomising groups of individuals to different interventions. Because the type of cluster may affect how well the intervention works (e.g. a free-school lunch programme may provide more benefit in public schools than in private schools), specification of the population of clusters, in addition to the population of individuals, may be required for the estimand definition.[ 3 - 8 ] Other issues have been noted in the literature, including specification of how individuals and clusters are weighted (e.g. whether interest lies in the individual-average or cluster-average treatment effect) [ 5 , 8 , 9 ] and how potential outcomes are summarised and contrasted (e.g., whether interest lies in the marginal or cluster-specific effect) [ 5 , 8 ]. Failure to address these additional items in CRTs could lead to ambiguous estimands, which in turn may cause misalignment of statistical estimation methods with the intended estimands and misinterpretation of results. There is a need to provide guidance on any additional items that need to be considered when defining estimands for CRTs that are not explicitly listed in the ICH E9 (R1) addendum. We therefore conducted a scoping review to identify a list of additional items that may need to be considered when defining estimands in CRTs. 2. Methods We conducted a scoping review to identify articles that described unique considerations for estimands in CRTs. The aim was to produce a list of additional items that may require consideration when defining estimands in these trials. 2.1. Eligibility Criteria Articles were eligible if they described an aspect of an estimand definition for CRTs which was not explicitly covered by one of the five attributes listed in the ICH E9 (R1) addendum. 2.2. Search strategy We used the following sources to identify eligible papers: (1) a systematic search of EMBASE, MEDLINE, Scopus, and the Web of Science databases, and (2) relevant papers from the authors’ personal libraries. For the database searches, the search strategy was developed in consultation with a research librarian. Two searchable concepts “ estimands” and “ cluster randomised trials” were chosen. For each concept, we identified synonyms and alternative terminology. The search required results to contain terms for both concepts. The full search strategy can be found in Appendix 1 in the Supplemental File. The search was performed in June 2024. One author (DB) assessed potential eligibility from the title and abstracts of identified articles and undertook full-text review to confirm eligibility. Queries regarding eligibility were discussed with at least one other author (BCK and/or AC). 2.3. Data extraction A data exaction form was developed and piloted (see Appendix 2 in the Supplemental File). In addition to a brief description of the article, we extracted information on any additional items that may need to be described when defining estimands for CRTs that were discussed in the article. One author completed the extractions (DB). Queries were discussed with at least one other author (BCK and/or AC), with disagreements resolved by discussion. 2.4. Analysis Data analysis was primarily descriptive. Any considerations that were relevant to the estimand definition for CRTs were recorded. This generated a list of potential items that may require consideration when defining estimands for CRTs beyond the five attributes listed in the ICH E9(R1) addendum. Results were reported in line with the PRISMA extension for scoping reviews.[ 10 ] 3. Results 3.1. Search results The database search identified 1294 articles ( Figure 1 ). After duplicates were removed, 613 articles underwent title and abstract screening, which resulted in 582 articles being excluded. The full text of the remaining 32 articles was screened for eligibility. After full-text screening, 24 articles were found to be eligible. Download figure Open in new tab Figure 1. Flow diagram of the search process An additional 48 articles were identified from authors’ personal libraries. After full-text screening, 26 articles were excluded either because they were duplicates of articles identified in the database search, or did not meet the eligibility criteria. This left 22 eligible articles. Combining the two sources resulted in 46 articles that were eligible to be included in this review ( Figure 1 ). The full list of these articles can be found in Appendix 3 in the Supplemental File. 3.2. Additional items that may need to be described for estimands in CRTs The review identified 8 additional items that may need to be considered when defining estimands in CRTs ( Table 1 ): View this table: View inline View popup Table 1. List of additional items which may require consideration when defining estimands for cluster randomised trials Population of clusters [ 5 , 7 , 11 ] Population of individuals under selection bias[ 3 , 4 , 6 , 12 , 13 ] Exposure time of individuals/clusters on treatment [ 14 - 18 ] How individuals and clusters are weighted (e.g. individual-average vs. cluster-average) [ 7 , 12 , 19 - 32 ] Whether summary measures are marginal or cluster-specific [ 5 , 11 , 27 , 28 , 33 - 39 ] Strategies used to handle cluster-level intercurrent events [ 5 , 40 - 43 ] How interference/spillover is handled [ 24 , 25 , 39 , 44 - 50 ] How individuals who leave or change clusters are handled [ 51 ] 4. Discussion In this scoping review, we set out to identify a list of additional items that may need to be considered when defining estimands for CRTs. After reviewing 46 articles, we found 8 additional items that may be relevant for CRTs. These items highlighted that for many CRTs there may be a need to further clarify certain aspects of the estimand, including aspects related to the population, treatment conditions, summary measure, and strategies to handle intercurrent events. For example, this review identified the need to further clarify the populations of interest in CRTs, including which individuals are part of the population of interest when there is selection bias, and which population of clusters is of interest; how intercurrent events at the level of the cluster, and how individuals who leave or change clusters, will be handled; how summary measures will be defined (e.g. whether individual-vs. cluster-average and marginal vs. cluster-specific effects are of interest); and how exposure time on treatment and interference/spill-over effects will be handled, when applicable. The items identified in this review can be used by investigators conducting CRTs to evaluate whether additional items should be considered when defining the estimand for their study, over and above the existing attributes listed in the ICH E9(R1) addendum. Consideration of these additional items could lead to less ambiguous estimands which make study results easier to interpret for end-users, such as clinicians, policy makers, and patients, and provide a clearer guide for investigators themselves on how to design and analyse their trial in line with study objectives. However, it should be noted that not all items will be relevant for all studies. For instance, some items, such as how estimands are defined when there is selection bias, or interference/spillover effects, will only be relevant in situations when these specific issues arise. This study highlights some important areas of future research. The ICH E9(R1) addendum provides important guidance for defining estimands, however, additional guidance for defining estimands in CRTs is essential to ensure estimands are clear and unambiguous in these trials. A consensus-extension of the ICH E9(R1) addendum for CRTs is currently underway [ 52 ], and the results from this scoping review will play an essential role in highlighting which additional items or attributes could be considered for inclusion in such guidance. Secondly, although there has been a wide range of methodological work around methods to estimate different estimands, it would be useful to collate such information together in tutorials or overview papers, to provide investigators with a clear list of options around which analyses could be implemented for specific estimands, along with the required assumptions of each analysis method. Strengths of this study include a comprehensive search of multiple databases and inclusion of articles from the authors’ personal libraries. However, we acknowledge that single reviewer screening could have resulted in some eligible articles being missed and that single data extracting could have resulted in information not being extracted comprehensively. To mitigate this risk, however, the final extraction results were checked by another reviewer (BK) which should help to minimise errors. Furthermore, due to the scoping nature of the search and the purpose of the review being to identify concepts that are relevant to the estimand definition for CRTs, single data extraction was deemed sufficient for this objective. 5. Conclusion This review has identified additional items that may need to be considered when defining estimands for CRTs. Study investigators undertaking CRTs should consider these items when defining estimands for their trials, to ensure estimands are unambiguous and relevant for end-users such as clinicians, patients, and policy makers. Data Availability All data produced in the present work are contained in the manuscript CRediT authorship contribution statement Dongquan Bi: Writing – original draft, Writing – review & editing, Data curation, Formal analysis, Methodology. Brennan Kahan: Writing – review & editing, Conceptualization, Supervision, Methodology. Andrew Copas: Writing – review & editing, Conceptualization, Supervision, Methodology. Fan Li: Writing – review & editing, Methodology. Declaration of competing interest There are no competing interests for any author. Funding sources DB, AC and BCK are funded by the UK Medical Research Council (grants MC_UU_00004/07 and MC_UU_00004/09). The funders had no role in the design and conduct of the study; collection, management, analysis, and interpretation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication. FL is funded by the Patient-Centered Outcomes Research Institute® (PCORI® Awards ME-2022C2-27676 & ME-2023C1-31350). The statements presented in this article are solely the responsibility of the authors and do not necessarily represent the views of PCORI®, its Board of Governors or Methodology Committee. Acknowledgments We thank Dr. Debora Marlett, the Training and Clinical Support Librarian from UCL Library Services for her advice on developing the search strategy. Reference 1. ↵ ICH E9 (R1) addendum on estimands and sensitivity analysis in clinical trials to the guideline on statistical principles for clinical trials Available from: https://www.ema.europa.eu/en/documents/scientific-guideline/ich-e9-r1-addendum-estimands-sensitivity-analysis-clinical-trials-guideline-statisticalprinciples_en.pdf 2. ↵ Kahan , B.C. , et al. , The estimands framework: a primer on the ICH E9(R1) addendum . BMJ , 2024 . 384 : p. e076316 . DOI: 10.1136/bmj-2023-076316 . OpenUrl FREE Full Text 3. ↵ Li , F. , et al. , Clarifying selection bias in cluster randomized trials . CLINICAL TRIALS , 2022 . 19 ( 1 ): p. 33 – 41 . DOI: 10.1177/17407745211056875 . OpenUrl CrossRef PubMed 4. ↵ Li , F. , et al. , A note on identification of causal effects in cluster randomized trials with post-randomization selection bias . COMMUNICATIONS IN STATISTICS-THEORY AND METHODS , 2024 . 53 ( 5 ): p. 1825 – 1837 . DOI: 10.1080/03610926.2022.2116281 . OpenUrl CrossRef 5. ↵ Kahan , B.C. , et al. , Demystifying estimands in cluster-randomised trials . Statistical Methods in Medical Research , 2024 . 33 ( 7 ): p. 1211 – 1232 . DOI: 10.1177/09622802241254197 . OpenUrl CrossRef PubMed 6. ↵ Schochet , P.Z. , Estimating average treatment effects for clustered RCTs with recruitment bias . Statistics in Medicine , 2024 . 43 ( 3 ): p. 452 - 474 . DOI: https://dx.doi.org/10.1002/sim.9957 . OpenUrl PubMed 7. ↵ Campbell , M.K. , et al. , Consort 2010 statement: extension to cluster randomised trials . Bmj-British Medical Journal , 2012 . 345 . DOI: 10.1136/bmj.e5661 . OpenUrl FREE Full Text 8. ↵ Bi , D. , A. Copas , and B.C. Kahan , Use of estimands in cluster randomised trials: a review . medRxiv , 2025 : p. 2025.06.10.25329251. DOI: 10.1101/2025.06.10.25329251 . OpenUrl Abstract / FREE Full Text 9. ↵ Kahan , B.C. , et al. , Estimands in cluster-randomized trials: choosing analyses that answer the right question . International Journal of Epidemiology , 2023 . 52 ( 1 ): p. 107 -+. DOI: 10.1093/ije/dyac131 . OpenUrl CrossRef PubMed 10. ↵ Tricco , A.C. , et al. , PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation . Ann Intern Med , 2018 . 169 ( 7 ): p. 467 – 473 . DOI: 10.7326/M18-0850 . OpenUrl CrossRef PubMed 11. ↵ Brown , A.W. , et al. , Best (but oft-forgotten) practices: designing, analyzing, and reporting cluster randomized controlled trials . AMERICAN JOURNAL OF CLINICAL NUTRITION , 2015 . 102 ( 2 ): p. 241 – 248 . DOI: 10.3945/ajcn.114.105072 . OpenUrl Abstract / FREE Full Text 12. ↵ Schochet , P.Z. , Estimating complier average causal effects for clustered RCTs when the treatment affects the service population . Journal of Causal Inference , 2022 . 10 ( 1 ): p. 300 – 334 . DOI: 10.1515/jci-2022-0033 . OpenUrl CrossRef 13. ↵ Papadogeorgou , G. , et al. , Addressing selection bias in cluster randomized experiments via weighting . arXiv e-prints , 2023 : p. arxiv: 2309.07365 . DOI: 10.48550/arXiv.2309.07365 . OpenUrl CrossRef 14. ↵ Hughes , J.P. , et al. , Sample Size Calculations for Stepped Wedge Designs with Treatment Effects that May Change with the Duration of Time under Intervention . PREVENTION SCIENCE , 2023 . DOI: 10.1007/s11121-023-01587-1 . OpenUrl CrossRef 15. Kenny , A. , et al. , Analysis of stepped wedge cluster randomized trials in the presence of a time-varying treatment effect . Statistics in Medicine , 2022 . 41 ( 22 ): p. 4311 – 4339 . DOI: 10.1002/sim.9511 . OpenUrl CrossRef PubMed 16. Maleyeff , L. , et al. , Assessing exposure-time treatment effect heterogeneity in stepped-wedge cluster randomized trials . Biometrics , 2023 . 79 ( 3 ): p. 2551 – 2564 . DOI: 10.1111/biom.13803 . OpenUrl CrossRef PubMed 17. Lee , K.M. and Y.B. Cheung , Cluster randomized trial designs for modeling time-varying intervention effects . Stat Med , 2024 . 43 ( 1 ): p. 49 – 60 . DOI: 10.1002/sim.9941 . OpenUrl CrossRef PubMed 18. ↵ Wang , B. , X. Wang , and F. Li , How to achieve model-robust inference in stepped wedge trials with model-based methods? arXiv e-prints , 2024 : p. arxiv: 2401.15680 . DOI: 10.48550/arXiv.2401.15680 . OpenUrl CrossRef 19. ↵ Su , F.Z. and P. Ding , Model-assisted analyses of cluster-randomized experiments . Journal of the Royal Statistical Society Series B-Statistical Methodology , 2021 . 83 ( 5 ): p. 994 – 1015 . DOI: 10.1111/rssb.12468 . OpenUrl CrossRef 20. Bugni , F. , et al. , Inference for cluster randomized experiments with non-ignorable cluster sizes . arXiv preprint ArXiv:2204.08356 , 2022 . 21. Wang , X. , et al. , Two weights make a wrong: Cluster randomized trials with variable cluster sizes and heterogeneous treatment effects . Contemporary Clinical Trials , 2022 . 114 : p. 106702 . DOI: https://dx.doi.org/10.1016/j.cct.2022.106702 . OpenUrl PubMed 22. Chen , X. and F. Li , Model-assisted analysis of covariance estimators for stepped wedge cluster randomized experiments . arXiv e-prints , 2023 : p. arxiv: 2306.11267 . DOI: 10.48550/arXiv.2306.11267 . OpenUrl CrossRef 23. Cheng , C. and F. Li , Semiparametric causal mediation analysis in cluster-randomized experiments . arXiv e-prints , 2024 : p. arxiv: 2404.18256 . DOI: 10.48550/arXiv.2404.18256 . OpenUrl CrossRef 24. ↵ Madrigal , A.M. , Cluster Allocation Design Networks . BAYESIAN ANALYSIS , 2007 . 2 ( 3 ): p. 557 – 589 . DOI: 10.1214/07-BA222 . OpenUrl CrossRef 25. ↵ Jiang , Z.C. , K. Imai , and A. Malani , Statistical inference and power analysis for direct and spillover effects in two-stage randomized experiments . BIOMETRICS , 2022 . DOI: 10.1111/biom.13782 . OpenUrl CrossRef 26. Benitez , A. , et al. , Defining and estimating effects in cluster randomized trials: A methods comparison . Statistics in Medicine , 2023 . 42 ( 19 ): p. 3443 – 3466 . DOI: 10.1002/sim.9813 . OpenUrl CrossRef PubMed 27. ↵ Hemming , K. and M. Taljaard , Commentary: Estimands in cluster trials: Thinking carefully about the target of inference and the consequences for analysis choice . International Journal of Epidemiology , 2023 . 52 ( 1 ): p. 116 – 118 . DOI: 10.1093/ije/dyac174 . OpenUrl CrossRef PubMed 28. ↵ Kahan , B.C. , et al. , Informative cluster size in cluster-randomised trials: A case study from the TRIGGER trial . Clinical Trials , 2023 . 20 ( 6 ): p. 661 – 669 . DOI: 10.1177/17407745231186094 . OpenUrl CrossRef PubMed 29. Kahan , B.C. , et al. , Demystifying estimands in cluster-randomised trials . Statistical Methods in Medical Research , 2024 . DOI: https://dx.doi.org/10.1177/09622802241254197 . 30. Kahan , B.C. , et al. , Estimands in cluster-randomized trials: Choosing analyses that answer the right question . International Journal of Epidemiology , 2023 . 52 ( 1 ): p. 107 – 118 . DOI: https://dx.doi.org/10.1093/ije/dyac131 . OpenUrl CrossRef PubMed 31. Wang , B.K. , et al. , Model-Robust and Efficient Covariate Adjustment for Cluster-Randomized Experiments . JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION , 2024 . DOI: 10.1080/01621459.2023.2289693 . OpenUrl CrossRef 32. ↵ Menglin Lee , K. and F. Li , How should parallel cluster randomized trials with a baseline period be analyzed? A survey of estimands and common estimators . arXiv e-prints , 2024 : p. arxiv: 2406.02028 . DOI: 10.48550/arXiv.2406.02028 . OpenUrl CrossRef 33. ↵ Bellamy , S.L. , et al. , Analysis of dichotomous outcome data for community intervention studies . Statistical Methods in Medical Research , 2000 . 9 ( 2 ): p. 135 - 159 . DOI : Doi 10.1191/096228000672549488 . OpenUrl CrossRef PubMed Web of Science 34. Ritz , J. and D. Spiegelman , Equivalence of conditional and marginal regression models for clustered and longitudinal data . Statistical Methods in Medical Research , 2004 . 13 ( 4 ): p. 309 – 323 . DOI: 10.1191/0962280204sm368ra . OpenUrl CrossRef Web of Science 35. Ukoumunne , O.C. , J.B. Carlin , and M.C. Gulliford , A simulation study of odds ratio estimation for binary outcomes from cluster randomized trials . Statistics in Medicine , 2007 . 26 ( 18 ): p. 3415 – 3428 . DOI: 10.1002/sim.2769 . OpenUrl CrossRef PubMed 36. Hubbard , A.E. , et al. , To GEE or Not to GEE . Epidemiology , 2010 . 21 ( 4 ): p. 467 – 474 . DOI: 10.1097/EDE.0b013e3181caeb90 . OpenUrl CrossRef PubMed Web of Science 37. Ma , J.H. , et al. , Comparison of population-averaged and cluster-specific models for the analysis of cluster randomized trials with missing binary outcomes: a simulation study . Bmc Medical Research Methodology , 2013 . 13 . DOI: 10.1186/1471-2288-13-117 . OpenUrl CrossRef PubMed 38. Muff , S. , L. Held , and L.F. Keller , Marginal or conditional regression models for correlated non-normal data? Methods in Ecology and Evolution , 2016 . 7 ( 12 ): p. 1514 – 1524 . DOI: 10.1111/2041-210x.12623 . OpenUrl CrossRef 39. ↵ Loeys , T. , S. Vansteelandt , and E. Goetghebeur , Accounting for correlation and compliance in cluster randomized trials . STATISTICS IN MEDICINE , 2001 . 20 ( 24 ): p. 3753 – 3767 . DOI: 10.1002/sim.1169 . OpenUrl CrossRef PubMed Web of Science 40. ↵ Brumback , B.A. , et al. , Using structural-nested models to estimate the effect of cluster-level adherence on individual-level outcomes with a three-armed cluster-randomized trial . Statistics in Medicine , 2014 . 33 ( 9 ): p. 1490 - 1502 . DOI: https://dx.doi.org/10.1002/sim.6049 . OpenUrl CrossRef PubMed 41. H. He , P. Wu , and D.G. Chen Helian , S. , et al. , Structural Nested Models for Cluster-Randomized Trials , in STATISTICAL CAUSAL INFERENCES AND THEIR APPLICATIONS IN PUBLIC HEALTH RESEARCH , H. He , P. Wu , and D.G. Chen , Editors. 2016 . p. 169 – 186 . 42. Agbla , S.C. and K. DiazOrdaz , Reporting non-adherence in cluster randomised trials: A systematic review . CLINICAL TRIALS , 2018 . 15 ( 3 ): p. 294 – 304 . DOI: 10.1177/1740774518761666 . OpenUrl CrossRef PubMed 43. ↵ Agbla , S.C. , B. De Stavola , and K. DiazOrdaz , Estimating cluster-level local average treatment effects in cluster randomised trials with non-adherence . Statistical Methods in Medical Research , 2020 . 29 ( 3 ): p. 911 - 933 . DOI: https://dx.doi.org/10.1177/0962280219849613 . OpenUrl PubMed 44. ↵ Hayes , R.J. , et al. , Design and analysis issues in cluster-randomized trials of interventions against infectious diseases . Stat Methods Med Res , 2000 . 9 ( 2 ): p. 95 – 116 . DOI: 10.1177/096228020000900203 . OpenUrl CrossRef PubMed Web of Science 45. Vanderweele , T.J. , et al. , Mediation and Spillover Effects in Group-Randomized Trials: A Case Study of the 4Rs Educational Intervention . JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION , 2013 . 108 ( 502 ): p. 469 – 482 . DOI: 10.1080/01621459.2013.779832 . OpenUrl CrossRef PubMed 46. Carnegie , N.B. , R. Wang , and V. De Gruttola , Estimation of the Overall Treatment Effect in the Presence of Interference in Cluster-Randomized Trials of Infectious Disease Prevention . Epidemiologic Methods , 2016 . 5 ( 1 ): p. 57 - 68 . DOI: https://dx.doi.org/10.1515/em-2015-0016 . OpenUrl PubMed 47. Kilpatrick , K.W. , M.G. Hudgens , and M.E. Halloran , Estimands and inference in cluster-randomized vaccine trials . Pharmaceutical Statistics , 2020 . 19 ( 5 ): p. 710 - 719 . DOI: https://dx.doi.org/10.1002/pst.2026 . OpenUrl PubMed 48. Keele , L. and H. Kang , An introduction to spillover effects in cluster randomized trials with noncompliance . CLINICAL TRIALS , 2022 . 19 ( 4 ): p. 375 – 379 . DOI: 10.1177/17407745221093580 . OpenUrl CrossRef PubMed 49. Wang , R. , et al. , Methods for the estimation of direct and indirect vaccination effects by combining data from individual- and cluster-randomized trials . Statistics in Medicine , 2024 . 43 ( 8 ): p. 1627 – 1639 . DOI: https://dx.doi.org/10.1002/sim.10030 . OpenUrl PubMed 50. ↵ Park , C. and H. Kang , Assumption-Lean Analysis of Cluster Randomized Trials in Infectious Diseases for Intent-to-Treat Effects and Network Effects . JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION , 2023 . 118 ( 542 ): p. 1195 – 1206 . DOI: 10.1080/01621459.2021.1983437 . OpenUrl CrossRef 51. ↵ Andridge , R.R. , et al. , Analytic methods for individually randomized group treatment trials and group-randomized trials when subjects belong to multiple groups . Statistics in Medicine , 2014 . 33 ( 13 ): p. 2178 – 2190 . DOI: 10.1002/sim.6083 . OpenUrl CrossRef PubMed 52. ↵ Kahan , B. , Consensus statement on reporting estimands for cluster randomised trials: the CRT-estimands study . 2024 . DOI: 10.17605/OSF.IO/A5KDY . OpenUrl CrossRef View the discussion thread. Back to top Previous Next Posted June 26, 2025. Download PDF Supplementary Material Data/Code Email Thank you for your interest in spreading the word about medRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following A scoping review identified additional considerations for defining estimands in cluster randomised trials Message Subject (Your Name) has forwarded a page to you from medRxiv Message Body (Your Name) thought you would like to see this page from the medRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share A scoping review identified additional considerations for defining estimands in cluster randomised trials Dongquan Bi , Andrew Copas , Fan Li , Brennan C Kahan medRxiv 2025.06.25.25330127; doi: https://doi.org/10.1101/2025.06.25.25330127 Share This Article: Copy Citation Tools A scoping review identified additional considerations for defining estimands in cluster randomised trials Dongquan Bi , Andrew Copas , Fan Li , Brennan C Kahan medRxiv 2025.06.25.25330127; doi: https://doi.org/10.1101/2025.06.25.25330127 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Public and Global Health Subject Areas All Articles Addiction Medicine (568) Allergy and Immunology (863) Anesthesia (298) Cardiovascular Medicine (4421) Dentistry and Oral Medicine (443) Dermatology (382) Emergency Medicine (607) Endocrinology (including Diabetes Mellitus and Metabolic Disease) (1507) Epidemiology (15215) Forensic Medicine (30) Gastroenterology (1122) Genetic and Genomic Medicine (6582) Geriatric Medicine (667) Health Economics (996) Health Informatics (4522) Health Policy (1366) Health Systems and Quality Improvement (1611) Hematology (540) HIV/AIDS (1264) Infectious Diseases (except HIV/AIDS) (15907) Intensive Care and Critical Care Medicine (1103) Medical Education (621) Medical Ethics (144) Nephrology (667) Neurology (6580) Nursing (345) Nutrition (998) Obstetrics and Gynecology (1143) Occupational and Environmental Health (956) Oncology (3328) Ophthalmology (970) Orthopedics (369) Otolaryngology (420) Pain Medicine (435) Palliative Medicine (129) Pathology (663) Pediatrics (1690) Pharmacology and Therapeutics (691) Primary Care Research (710) Psychiatry and Clinical Psychology (5436) Public and Global Health (9215) Radiology and Imaging (2193) Rehabilitation Medicine and Physical Therapy (1368) Respiratory Medicine (1194) Rheumatology (593) Sexual and Reproductive Health (709) Sports Medicine (529) Surgery (709) Toxicology (99) Transplantation (288) Urology (265) (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9ff6fbd13a58c13d',t:'MTc3OTQwMjE4Ng=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();