دورية أكاديمية
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.
العنوان: | 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. |
---|---|
المؤلفون: | Golzarri-Arroyo L; Department of Epidemiology and Biostatistics, Indiana University School of Public Health-Bloomington USA. Electronic address: lgolzarr@indiana.edu., Dickinson SL; Department of Epidemiology and Biostatistics, Indiana University School of Public Health-Bloomington USA., Jamshidi-Naeini Y; Department of Epidemiology and Biostatistics, Indiana University School of Public Health-Bloomington USA., Zoh RS; Department of Epidemiology and Biostatistics, Indiana University School of Public Health-Bloomington USA., Brown AW; Department of Applied Health Science, Indiana University School of Public Health-Bloomington USA., Owora AH; Department of Epidemiology and Biostatistics, Indiana University School of Public Health-Bloomington USA., Li P; School of Nursing, University of Alabama at Birmingham USA., Oakes JM; School of Public Health, University of Minnesota USA., Allison DB; Department of Epidemiology and Biostatistics, Indiana University School of Public Health-Bloomington USA. |
المصدر: | Computer methods and programs in biomedicine [Comput Methods Programs Biomed] 2022 Mar; Vol. 215, pp. 106654. Date of Electronic Publication: 2022 Jan 21. |
نوع المنشور: | Journal Article; Randomized Controlled Trial |
اللغة: | English |
بيانات الدورية: | Publisher: Elsevier Scientific Publishers Country of Publication: Ireland NLM ID: 8506513 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1872-7565 (Electronic) Linking ISSN: 01692607 NLM ISO Abbreviation: Comput Methods Programs Biomed Subsets: MEDLINE |
أسماء مطبوعة: | Publication: Limerick : Elsevier Scientific Publishers Original Publication: Amsterdam : Elsevier Science Publishers, c1984- |
مواضيع طبية MeSH: | Research Design*, Cluster Analysis ; Computer Simulation ; Humans ; Linear Models ; Sample Size |
مستخلص: | 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. Competing Interests: Declaration of Competing Interests The authors declare that they have no conflicts of interest. (Copyright © 2022 Elsevier B.V. All rights reserved.) |
References: | Stat Med. 1998 Jul 30;17(14):1581-600. (PMID: 9699231) Dtsch Arztebl Int. 2018 Mar 9;115(10):163-168. (PMID: 29587960) Educ Psychol Meas. 2018 Apr;78(2):297-318. (PMID: 29795957) Child Obes. 2017 Aug;13(4):300-313. (PMID: 28448174) Child Obes. 2020 Mar;16(2):65-66. (PMID: 32078372) Int J Epidemiol. 2018 Feb 1;47(1):321-331. (PMID: 29025158) Ann Behav Med. 2020 Jan 24;54(2):139. (PMID: 31880299) Eur J Pediatr. 2020 Sep;179(9):1487-1488. (PMID: 32078037) Stat Med. 2001 Feb 15;20(3):453-72. (PMID: 11180313) Biostatistics. 2021 Feb 02;:. (PMID: 33527999) BMC Med Res Methodol. 2009 Jun 16;9:37. (PMID: 19531226) Am J Clin Nutr. 2015 Aug;102(2):241-8. (PMID: 26016864) BMC Med Res Methodol. 2015 Apr 23;15:38. (PMID: 25899170) Stat Methods Med Res. 2021 Feb;30(2):612-639. (PMID: 32631142) BMC Health Serv Res. 2004 Nov 18;4(1):33. (PMID: 15550169) Am J Public Health. 2004 Mar;94(3):423-32. (PMID: 14998806) Multivariate Behav Res. 2016 Jul-Aug;51(4):495-518. (PMID: 27269278) BMJ. 2017 Jul 14;358:j3064. (PMID: 28710062) Stat Med. 2007 Jan 15;26(1):2-19. (PMID: 17136746) Am J Public Health. 2004 Mar;94(3):416-22. (PMID: 14998805) Trials. 2016 Sep 06;17(1):438. (PMID: 27600609) |
معلومات مُعتمدة: | R25 GM141507 United States GM NIGMS NIH HHS; R25 DK099080 United States DK NIDDK NIH HHS; U24 AG056053 United States AG NIA NIH HHS; P30 AG050886 United States AG NIA NIH HHS; R25 HL124208 United States HL NHLBI NIH HHS; K12 HS026390 United States HS AHRQ HHS |
تواريخ الأحداث: | Date Created: 20220130 Date Completed: 20220216 Latest Revision: 20230302 |
رمز التحديث: | 20231215 |
مُعرف محوري في PubMed: | PMC8847311 |
DOI: | 10.1016/j.cmpb.2022.106654 |
PMID: | 35093646 |
قاعدة البيانات: | MEDLINE |
تدمد: | 1872-7565 |
---|---|
DOI: | 10.1016/j.cmpb.2022.106654 |