Cluster randomized trials: Considerations for design and analysis

被引：6
作者：
Chakraborty H. [1 ]
Lyons G. [1 ]
机构：
[1] Department of Epidemiology and Biostatistics, Arnold School of Public Health, University of South Carolina, 915 Green Street, Columbia, 29208, SC
来源：
Journal of Statistical Theory and Practice | 2015年 / 9卷 / 3期
关键词：
Analysis; Cluster randomized trials; Intracluster correlation; Sample size estimation; Statistical design;
D O I：
10.1080/15598608.2014.992081
中图分类号：
学科分类号：
摘要：
Scientists often use randomized controlled trials to compare a newly developed treatment to the existing one, or to a placebo. Patients are randomly assigned to a treatment, and they are compared with respect to the outcome of interest. The cluster randomized trial (CRT) is a type of randomized controlled trial in which the treatments are randomized at the group, rather than individual, level. The intracluster correlation (ICC) measures the degree of similarity between individuals within clusters. CRTs can be designed in several ways; it is essential that researchers carefully plan the study, from sample size calculations to ICC calculation to analysis, in order to get valid and meaningful results. In this article we review and discuss the considerations essential to conducting a successful CRT using both frequentist and Bayesian approaches, and we discuss recent trends in CRT analysis, including highlighting new methodology for both binary and continuous data. © Grace Scientific Publishing, LLC.
引用
收藏
页码：685 / 698
页数：13
相关论文
共 107 条
  • [41] Ennett S.T., Tobler N.S., Ringwalt C.L., Flewelling R.L., How effective is drug abuse resistance education? A meta-analysis of Project DARE outcome evaluations, Am. J. Public Health, 84, 9, pp. 1394-1401, (1994)
  • [42] Evans B.A., Feng Z., Peterson A.V., A comparison of generalized linear mixed model procedures with estimating equations for variance and covariance parameter estimation in longitudinal studies and group randomized trials, Stat. Med., 20, pp. 3353-3373, (2001)
  • [43] Feng Z., Diehr P., Yasui Y., Evans B., Beresford S., Koepsell T.D., Explaining community-level variance in group randomized trials, Stat. Med., 18, 5, pp. 539-556, (1999)
  • [44] Fisher R., Statistical Methods for Research Workers, (1925)
  • [45] Fleiss J.L., Reliability of measurement, The Design and Analysis of Clinical Experiments, pp. 1-32, (1986)
  • [46] Fleiss J.L., Cuzick J., The reliability of dichotomous judgments: Unequal numbers of judges per subject, Appl. Psychol. Meas., 3, 4, pp. 537-542, (1979)
  • [47] Gail M., Byar D., Pechaceck T., Corle D., Aspects of statistical design for the community intervention trial for smoking cessation (COMMIT), Control Clin. Trials, 13, pp. 6-21, (1992)
  • [48] Gilbody S., Bower P., Torgerson D., Richards D., Cluster randomized trials produced similar results to individually randomized trials in a meta-analysis of enhanced care for depression, J. Clin. Epidemiol., 61, 2, pp. 160-168, (2008)
  • [49] Goldstein H., Multilevel Statistical Models, (1995)
  • [50] Gulliford M.C., Adams G., Ukoumunne O.C., Latinovic R., Chinn S., Campbell M.J., Intraclass correlation coefficient and outcome prevalence are associated in clustered binary data, J. Clin. Epidemiol., 58, 3, pp. 246-251, (2005)
12345678910