Literature DB >> 35093646

Evaluation of the type I error rate when using parametric bootstrap analysis of a cluster randomized controlled trial with binary outcomes and a small number of clusters.

Lilian Golzarri-Arroyo1, Stephanie L Dickinson2, Yasaman Jamshidi-Naeini2, Roger S Zoh2, Andrew W Brown3, Arthur H Owora2, Peng Li4, J Michael Oakes5, David B Allison2.   

Abstract

BACKGROUND: Cluster randomized controlled trials (cRCTs) are increasingly used but must be analyzed carefully. We conducted a simulation study to evaluate the validity of a parametric bootstrap (PB) approach with respect to the empirical type I error rate for a cRCT with binary outcomes and a small number of clusters.
METHODS: We simulated a case study with a binary (0/1) outcome, four clusters, and 100 subjects per cluster. To compare the validity of the test with respect to error rate, we simulated the same experiment with K=10, 20, and 30 clusters, each with 2,000 simulated datasets. To test the null hypothesis, we used a generalized linear mixed model including a random intercept for clusters and obtained p-values based on likelihood ratio tests (LRTs) using the parametric bootstrap method as implemented in the R package "pbkrtest".
RESULTS: The PB test produced error rates of 9.1%, 5.5%, 4.9%, and 5.0% on average across all ICC values for K=4, K=10, K=20, and K=30, respectively. The error rates were higher, ranging from 9.1% to 36.5% for K=4, in the models with singular fits (i.e., ignoring clustering) because the ICC was estimated to be zero.
CONCLUSION: Using the parametric bootstrap for cRCTs with a small number of clusters results in inflated error rates and is not valid.
Copyright © 2022 Elsevier B.V. All rights reserved.

Entities:  

Mesh:

Year:  2022        PMID: 35093646      PMCID: PMC8847311          DOI: 10.1016/j.cmpb.2022.106654

Source DB:  PubMed          Journal:  Comput Methods Programs Biomed        ISSN: 0169-2607            Impact factor:   7.027


  21 in total

1.  Bayesian methods of analysis for cluster randomized trials with binary outcome data.

Authors:  R M Turner; R Z Omar; S G Thompson
Journal:  Stat Med       Date:  2001-02-15       Impact factor: 2.373

2.  Analysis of data from group-randomized trials with repeat observations on the same groups.

Authors:  D M Murray; P J Hannan; R D Wolfinger; W L Baker; J H Dwyer
Journal:  Stat Med       Date:  1998-07-30       Impact factor: 2.373

3.  Incorrect design and analysis render conclusion unsubstantiated: comment on "A digital movement in the world of inactive children: favourable outcomes of playing active video games in a pilot randomized trial".

Authors:  Lilian Golzarri-Arroyo; Colby J Vorland; Lehana Thabane; J Michael Oakes; Ethan T Hunt; Andrew W Brown; David B Allison
Journal:  Eur J Pediatr       Date:  2020-02-20       Impact factor: 3.183

4.  A School-Based, Peer-Led, Social Marketing Intervention To Engage Spanish Adolescents in a Healthy Lifestyle ("We Are Cool"-Som la Pera Study): A Parallel-Cluster Randomized Controlled Study.

Authors:  Magaly Aceves-Martins; Elisabet Llauradó; Lucia Tarro; David Moriña; Ignasi Papell-Garcia; Jordi Prades-Tena; Helle Kettner-Høeberg; Francesc Puiggròs; Lluís Arola; Amy Davies; Montse Giralt; Rosa Solà
Journal:  Child Obes       Date:  2017-04-27       Impact factor: 2.992

5.  Using Cluster Bootstrapping to Analyze Nested Data With a Few Clusters.

Authors:  Francis L Huang
Journal:  Educ Psychol Meas       Date:  2016-11-24       Impact factor: 2.821

6.  Cluster randomized trials with a small number of clusters: which analyses should be used?

Authors:  Clémence Leyrat; Katy E Morgan; Baptiste Leurent; Brennan C Kahan
Journal:  Int J Epidemiol       Date:  2018-02-01       Impact factor: 7.196

Review 7.  Cluster-Randomized Studies.

Authors:  Eva Lorenz; Sascha Köpke; Holger Pfaff; Maria Blettner
Journal:  Dtsch Arztebl Int       Date:  2018-03-09       Impact factor: 5.594

8.  Randomization by Cluster, But Analysis by Individual Without Accommodating Clustering in the Analysis Is Incorrect: Comment.

Authors:  Carmen D Tekwe; David B Allison
Journal:  Ann Behav Med       Date:  2020-01-24

9.  Incorrect Analyses of Cluster-Randomized Trials that Do Not Take Clustering and Nesting into Account Likely Lead to p-Values that Are Too Small.

Authors:  Lilian Golzarri-Arroyo; J Michael Oakes; Andrew W Brown; David B Allison
Journal:  Child Obes       Date:  2020-03       Impact factor: 2.992

10.  Marginal modeling of cluster-period means and intraclass correlations in stepped wedge designs with binary outcomes.

Authors:  Fan Li; Hengshi Yu; Paul J Rathouz; Elizabeth L Turner; John S Preisser
Journal:  Biostatistics       Date:  2022-07-18       Impact factor: 5.279

View more
  2 in total

1.  A practical decision tree to support editorial adjudication of submitted parallel cluster randomized controlled trials.

Authors:  Yasaman Jamshidi-Naeini; Andrew W Brown; Tapan Mehta; Deborah H Glueck; Lilian Golzarri-Arroyo; Keith E Muller; Carmen D Tekwe; David B Allison
Journal:  Obesity (Silver Spring)       Date:  2022-03       Impact factor: 9.298

2.  Re-analysis of data from a cluster RCT entitled "health literacy and exercise-focused interventions on clinical measurements in Chinese diabetes patients".

Authors:  Yasaman Jamshidi-Naeini; Lilian Golzarri-Arroyo; Colby J Vorland; Andrew W Brown; David B Allison
Journal:  EClinicalMedicine       Date:  2022-10-06
  2 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.