Inclusion of unexposed clusters improves the precision of fixed effects analysis of stepped-wedge cluster randomized trials with binary and count outcomes.
Binary outcomes
Cluster randomized trials
Count outcomes
Fixed effects model
Generalized linear model
Precision
Stepped wedge trials
Journal
BMC medical research methodology
ISSN: 1471-2288
Titre abrégé: BMC Med Res Methodol
Pays: England
ID NLM: 100968545
Informations de publication
Date de publication:
28 Oct 2024
28 Oct 2024
Historique:
received:
12
02
2024
accepted:
21
10
2024
medline:
29
10
2024
pubmed:
29
10
2024
entrez:
29
10
2024
Statut:
epublish
Résumé
The fixed effects model is a useful alternative to the mixed effects model for analyzing stepped-wedge cluster randomized trials (SW-CRTs). It controls for all time-invariant cluster-level confounders and has proper control of type I error when the number of clusters is small. While all clusters in a SW-CRT are typically designed to crossover from the control to receive the intervention, some trials can end with unexposed clusters (clusters that never receive the intervention), such as when a trial is terminated early due to safety concerns. It was previously unclear whether unexposed clusters would contribute to the estimation of the intervention effect in a fixed effects analysis. However, recent work has demonstrated that including an unexposed cluster can improve the precision of the intervention effect estimator in a fixed effects analysis of SW-CRTs with continuous outcomes. Still, SW-CRTs are commonly designed with binary outcomes and it is unknown if those previous results extend to SW-CRTs with non-continuous outcomes. In this article, we mathematically prove that the inclusion of unexposed clusters improves the precision of the fixed effects intervention effect estimator for SW-CRTs with binary and count outcomes. We then explore the benefits of including an unexposed cluster in simulated datasets with binary or count outcomes and a real palliative care data example with binary outcomes. The simulations show that including unexposed clusters leads to tangible improvements in the precision, power, and root mean square error of the intervention effect estimator. The inclusion of the unexposed cluster in the SW-CRT of a novel palliative care intervention with binary outcomes yielded smaller standard errors and narrower 95% Wald Confidence Intervals. In this article, we demonstrate that the inclusion of unexposed clusters in the fixed effects analysis can lead to the improvements in precision, power, and RMSE of the fixed effects intervention effect estimator for SW-CRTs with binary or count outcomes.
Sections du résumé
BACKGROUND
BACKGROUND
The fixed effects model is a useful alternative to the mixed effects model for analyzing stepped-wedge cluster randomized trials (SW-CRTs). It controls for all time-invariant cluster-level confounders and has proper control of type I error when the number of clusters is small. While all clusters in a SW-CRT are typically designed to crossover from the control to receive the intervention, some trials can end with unexposed clusters (clusters that never receive the intervention), such as when a trial is terminated early due to safety concerns. It was previously unclear whether unexposed clusters would contribute to the estimation of the intervention effect in a fixed effects analysis. However, recent work has demonstrated that including an unexposed cluster can improve the precision of the intervention effect estimator in a fixed effects analysis of SW-CRTs with continuous outcomes. Still, SW-CRTs are commonly designed with binary outcomes and it is unknown if those previous results extend to SW-CRTs with non-continuous outcomes.
METHODS
METHODS
In this article, we mathematically prove that the inclusion of unexposed clusters improves the precision of the fixed effects intervention effect estimator for SW-CRTs with binary and count outcomes. We then explore the benefits of including an unexposed cluster in simulated datasets with binary or count outcomes and a real palliative care data example with binary outcomes.
RESULTS
RESULTS
The simulations show that including unexposed clusters leads to tangible improvements in the precision, power, and root mean square error of the intervention effect estimator. The inclusion of the unexposed cluster in the SW-CRT of a novel palliative care intervention with binary outcomes yielded smaller standard errors and narrower 95% Wald Confidence Intervals.
CONCLUSIONS
CONCLUSIONS
In this article, we demonstrate that the inclusion of unexposed clusters in the fixed effects analysis can lead to the improvements in precision, power, and RMSE of the fixed effects intervention effect estimator for SW-CRTs with binary or count outcomes.
Identifiants
pubmed: 39468446
doi: 10.1186/s12874-024-02379-z
pii: 10.1186/s12874-024-02379-z
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
254Subventions
Organisme : National Medical Research Council
ID : MOH-000526
Informations de copyright
© 2024. The Author(s).
Références
Hayes RJ, Moulton LH. Cluster randomised trials. Subjects Bioscience, Mathematics & Statistics, Medicine, Dentistry, Nursing & Allied Health. 2nd ed. New York: Imprint Chapman and Hall/CRC; 2017. p. 424. (Chapman & hall/crc biostatistics series). https://doi.org/10.4324/9781315370286 . https://www.taylorfrancis.com/books/mono/10.4324/9781315370286/cluster-randomised-trials-richard-hayes-lawrence-moulton .
Hussey MA, Hughes JP. Design and analysis of stepped wedge cluster randomized trials. Contemp Clin Trials. 2007;28(2):182–91.
doi: 10.1016/j.cct.2006.05.007
pubmed: 16829207
Li F, Hughes JP, Hemming K, Taljaard M, Melnick ER, Heagerty PJ. Mixed-effects models for the design and analysis of stepped wedge cluster randomized trials: an overview. Stat Methods Med Res. 2021;30(2):612–39.
doi: 10.1177/0962280220932962
pubmed: 32631142
Hausman JA. Specification tests in econometrics. Econometrica. 1978;46(6):1251–71.
doi: 10.2307/1913827
Allison PD. Fixed effects regression methods for longitudinal data using SAS. Cary, NC: SAS; 2005. p. 148.
Gardiner JC, Luo Z, Roman LA. Fixed effects, random effects and GEE: what are the differences? Stat Med. 2009;28(2):221–39.
doi: 10.1002/sim.3478
pubmed: 19012297
Gunasekara FI, Richardson K, Carter K, Blakely T. Fixed effects analysis of repeated measures data. Int J Epidemiol. 2014;43(1):264–9.
doi: 10.1093/ije/dyt221
pubmed: 24366487
Wooldridge JM. Econometric Analysis of Cross Section and Panel Data. 2nd ed. Cambridge, Mass: MIT Press; 2010. p. 1064.
Taljaard M, Teerenstra S, Ivers NM, Fergusson DA. Substantial risks associated with few clusters in cluster randomized and stepped wedge designs. Clin Trials. 2016;13(4):459–63.
doi: 10.1177/1740774516634316
pubmed: 26940696
Deaton A, Cartwright N. Understanding and misunderstanding randomized controlled trials. Soc Sci Med. 2018;210:2–21.
doi: 10.1016/j.socscimed.2017.12.005
pubmed: 29331519
Hemming K, Taljaard M. Reflection on modern methods: when is a stepped-wedge cluster randomized trial a good study design choice? Int J Epidemiol. 2020;49(3):1043–52.
doi: 10.1093/ije/dyaa077
pubmed: 32386407
pmcid: 7394949
Barker D, McElduff P, D’Este C, Campbell MJ. Stepped wedge cluster randomised trials: a review of the statistical methodology used and available. BMC Med Res Methodol. 2016;16(1):69.
doi: 10.1186/s12874-016-0176-5
pubmed: 27267471
pmcid: 4895892
Nevins P, Davis-Plourde K, Pereira Macedo JA, Ouyang Y, Ryan M, Tong G, et al. A scoping review described diversity in methods of randomization and reporting of baseline balance in stepped-wedge cluster randomized trials. J Clin Epidemiol. 2023;157:134–45.
doi: 10.1016/j.jclinepi.2023.03.010
pubmed: 36931478
pmcid: 10546924
Barker D, D’Este C, Campbell MJ, McElduff P. Minimum number of clusters and comparison of analysis methods for cross sectional stepped wedge cluster randomised trials with binary outcomes: a simulation study. Trials. 2017;18(1):1–11.
doi: 10.1186/s13063-017-1862-2
Leyrat C, Morgan KE, Leurent B, Kahan BC. Cluster randomized trials with a small number of clusters: which analyses should be used? Int J Epidemiol. 2018;47(1):321–31.
doi: 10.1093/ije/dyx169
pubmed: 29025158
Thompson JA, Davey C, Fielding KL, Hargreaves JR, Hayes RJ. Robust analysis of stepped wedge trials using cluster-level summaries within periods. Stat Med. 2018;37(16):2487–500.
doi: 10.1002/sim.7668
pubmed: 29635789
pmcid: 6032886
Craine N, Whitaker R, Perrett S, Zou L, Hickman M, Lyons M. A stepped wedge cluster randomized control trial of dried blood spot testing to improve the uptake of hepatitis C antibody testing within UK prisons. Eur J Public Health. 2015;25(2):351–7.
doi: 10.1093/eurpub/cku096
pubmed: 25061233
Kelly PJ, Baker AL, Deane FP, Callister R, Collins CE, Oldmeadow C, et al. Study protocol: a stepped wedge cluster randomised controlled trial of a healthy lifestyle intervention for people attending residential substance abuse treatment. BMC Public Health. 2015;15(1):465.
doi: 10.1186/s12889-015-1729-y
pubmed: 25935830
pmcid: 4433090
The CIPHER, Investigators, Williamson A, Redman S, Haynes A, Barker D, Jorm L, et al. Supporting policy in health with Research: an intervention trial (SPIRIT)--protocol for a stepped wedge trial. BMJ Open. 2014;4(7):e005293-005293.
doi: 10.1136/bmjopen-2014-005293
Groshaus H, Boscan A, Khandwala F, Holroyd-Leduc J. Use of clinical decision support to improve the quality of Care provided to older hospitalized patients. Appl Clin Inf. 2012;03(01):94–102.
doi: 10.4338/ACI-2011-08-RA-0047
Hill TD, Davis AP, Roos JM, French MT. Limitations of fixed-effects models for Panel Data. Sociol Perspect. 2020;63(3):357–69.
doi: 10.1177/0731121419863785
Forbes H, Douglas I, Finn A, Breuer J, Bhaskaran K, Smeeth L, et al. Risk of herpes zoster after exposure to varicella to explore the exogenous boosting hypothesis: self controlled case series study using UK electronic healthcare data. BMJ. 2020;368:l6987.
doi: 10.1136/bmj.l6987
pubmed: 31969318
pmcid: 7190015
Cissé B, Ba EH, Sokhna C, NDiaye JL, Gomis JF, Dial Y, et al. Effectiveness of seasonal malaria chemoprevention in children under ten years of age in senegal: a stepped-wedge cluster-randomised trial. PLoS Med. 2016;13(11):e1002175.
doi: 10.1371/journal.pmed.1002175
pubmed: 27875528
pmcid: 5119693
Girling AJ, Hemming K. Statistical efficiency and optimal design for stepped cluster studies under linear mixed effects models. Stat Med. 2016;35(13):2149–66.
doi: 10.1002/sim.6850
pubmed: 26748662
pmcid: 4949721
Thompson JA, Fielding K, Hargreaves J, Copas A. The optimal design of stepped wedge trials with equal allocation to sequences and a comparison to other trial designs. Clin Trials. 2017;14(6):639–47.
doi: 10.1177/1740774517723921
pubmed: 28797179
pmcid: 5718336
Lee KM, Ma X, Yang GM, Cheung YB. Inclusion of unexposed clusters improves the precision of fixed effects analysis of stepped-wedge cluster randomized trials. Stat Med. 2022;41(15):2923–38.
Robinson LD, Jewell NP. Some surprising results about covariate adjustment in logistic regression models. Int Stat Rev Rev Int Stat. 1991;59(2):227–40.
doi: 10.2307/1403444
Horn RA, Johnson CR. Matrix analysis. Second edition, corrected reprint. New York, NY: Cambridge University Press; 2017. p. 643.
Goldstein H, Browne W, Rasbash J. Partitioning variation in Multilevel models. Underst Stat. 2002;1(4):223–31.
doi: 10.1207/S15328031US0104_02
Nakagawa S, Johnson PCD, Schielzeth H. The coefficient of determination R2 and intra-class correlation coefficient from generalized linear mixed-effects models revisited and expanded. J R Soc Interface. 2017;14(134):20170213.
doi: 10.1098/rsif.2017.0213
pubmed: 28904005
pmcid: 5636267
Yang GM, Zhou S, Xu Z, Goh SSL, Zhu X, Chong DQQ, et al. Comparing the effect of a consult model versus an integrated palliative care and medical oncology co-rounding model on health care utilization in an acute hospital – an open-label stepped-wedge cluster-randomized trial. Palliat Med. 2021;35(8):1578–89.
doi: 10.1177/02692163211022957
pubmed: 34524044
Vaisey S, Miles A. What you can—and can’t—Do with three-Wave Panel Data. Sociol Methods Res. 2017;46(1):44–67.
doi: 10.1177/0049124114547769
DiDiodato G, McArthur L, Beyene J, Smieja M, Thabane L. Evaluating the impact of an antimicrobial stewardship program on the length of stay of immune-competent adult patients admitted to a hospital ward with a diagnosis of community-acquired pneumonia: a quasi-experimental study. Am J Infect Control. 2016;44(5):e73-79.
doi: 10.1016/j.ajic.2015.12.026
pubmed: 26899527
Hooper R, Teerenstra S, de Hoop E, Eldridge S. Sample size calculation for stepped wedge and other longitudinal cluster randomised trials. Stat Med. 2016;35(26):4718–28.
doi: 10.1002/sim.7028
pubmed: 27350420
Hemming K, Taljaard M, McKenzie JE, Hooper R, Copas A, Thompson JA, et al. Reporting of stepped wedge cluster randomised trials: extension of the CONSORT 2010 statement with explanation and elaboration. BMJ. 2018;363:k1614.
doi: 10.1136/bmj.k1614
pubmed: 30413417
pmcid: 6225589