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
  • [1] Adams G., Gulliford M.C., Ukoumunne O.C., Eldridge S., Chinn S., Campbell M.J., Patterns of intra-cluster correlation from primary care research to inform study design and analysis, J. Clin. Epidemiol., 57, 8, pp. 785-794, (2004)
  • [2] Ahmed M., Shoukri M., A Bayesian estimator of the intracluster correlation coefficient from correlated binary responses, J. Data Sci., 8, pp. 127-137, (2010)
  • [3] Althabe F., Buekens P., Bergel E., Belizan J.M., Kropp N., Wright L., Et al., A cluster randomized controlled trial of a behavioral intervention to facilitate the development and implementation of clinical practice guidelines in Latin American maternity hospitals: The Guidelines Trial: Study protocol, BMC Womens Health, 5, 1, (2005)
  • [4] Altham P.M.E., Two generalizations of the binomial distribution, J. R. Stat. Soc. Ser. C, 27, 2, pp. 162-167, (1978)
  • [5] Bansal N.K., Bhandary M.K., Bayes estimation of intraclass correlation coefficient, Commun. Stat.Theory Methods, 29, 1, pp. 79-93, (2000)
  • [6] Bansal N.K., Bhandary M., Fujiwara K., Bayes estimation of intraclass correlation coefficients under unequal family sizes, Commun. Stat. Simul. Comput., 42, 2, pp. 294-302, (2013)
  • [7] Baskerville N.B., Hogg W., Lemelin J., The effect of cluster randomization on sample size in prevention research, J. Family Pract., 50, 3, (2001)
  • [8] Bland J.M., Cluster randomised trials in the medical literature: Two bibliometric surveys, BMC Med. Res. Methodol., 13, 4, (2004)
  • [9] Bryk A., Raudenbush S., Hierarchical Linear Models: Applications and Data Analysis Methods, (1992)
  • [10] Cals J.W.L., Butler C.C., Hopstaken R.M., Hood K., Dinant G.-J., Effect of point of care testing for C reactive protein and training in communication skills on antibiotic use in lower respiratory tract infections: Cluster randomised trial, Br. Med J., 338, (2009)
12345678910