Advertisement

Journal of Statistical Theory and Practice

, Volume 9, Issue 3, pp 685–698 | Cite as

Cluster Randomized Trials: Considerations for Design and Analysis

  • Hrishikesh Chakraborty
  • Genevieve Lyons
Article

Abstract

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.

Keywords

Cluster randomized trials Intracluster correlation Statistical design Sample size estimation Analysis 

AMS Subject Classification

62P10 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Adams, G., M. C. Gulliford, O.C. Ukoumunne, S. Eldridge, S. Chinn, and M. J. Campbell. 2004. Patterns of intra-cluster correlation from primary care research to inform study design and analysis. J. Clin. Epidemiol., 57(8), 785–94.CrossRefGoogle Scholar
  2. Ahmed, M., and M. Shoukri. 2010. A Bayesian estimator of the intracluster correlation coefficient from correlated binary responses. J. Data Sci., 8, 127–137.Google Scholar
  3. Althabe, F., P. Buekens, E. Bergel, J. M. Belizán, N. Kropp, L. Wright, et al. 2005. 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), 4.CrossRefGoogle Scholar
  4. Altham, P. M. E. 1978. Two generalizations of the binomial distribution. J. R. Stat. Soc. Ser. C, 27(2), 162–167.MathSciNetzbMATHGoogle Scholar
  5. Bansal, N. K., and M. K. Bhandary. 2000. Bayes estimation of intraclass correlation coefficient. Commun. Stat. Theory Methods, 29(1), 79–93.MathSciNetzbMATHCrossRefGoogle Scholar
  6. Bansal, N. K., M. Bhandary, and K. Fujiwara. 2013. Bayes estimation of intraclass correlation coefficients under unequal family sizes. Commun. Stat. Simul. Comput., 42(2), 294–302.MathSciNetzbMATHCrossRefGoogle Scholar
  7. Baskerville, N. B., W. Hogg, and J. Lemelin. 2001. The effect of cluster randomization on sample size in prevention research. J. Family Pract., 50(3), 242.Google Scholar
  8. Bland, J. M. 2004. Cluster randomised trials in the medical literature: Two bibliometric surveys. BMC Med. Res. Methodol., 13(4), 21.CrossRefGoogle Scholar
  9. Bryk, A., and S. Raudenbush. 1992. Hierarchical linear models: Applications and data analysis methods. Newbury Park, CA: Sage.Google Scholar
  10. Cals, J. W. L., C. C. Butler, R. M. Hopstaken, K. Hood, and G.-J. Dinant. 2009. 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, b1374.CrossRefGoogle Scholar
  11. Campbell, M. J., A. Donner, and N. Klar. 2007. Developments in cluster randomized trials and Statistics in Medicine. Stat. Med., 26, 2–19.MathSciNetCrossRefGoogle Scholar
  12. Campbell, M. K., J. M. Grimshaw, and D. R. Elbourne. 2004. Intracluster correlation coefficients in cluster randomized trials: Empirical insights into how should they be reported. BMC Med. Res. Methodol., 4(9), 702–708.Google Scholar
  13. Carlo, W. A., S. S. Goudar, I. Jehan, E. Chomba, A. Tshefu, A. Garces, et al. 2010. Newborn-care training and perinatal mortality in developing countries. N. Engl. J. Med., 362(7), 614–623.CrossRefGoogle Scholar
  14. Carrol, R., and D. Ruppert. 1988. Transformation and weighting in regression. London, UK: Chapman and Hall.CrossRefGoogle Scholar
  15. Chakraborty, H. 2008a. Cluster-randomized trial of a community-based intervention. Lancet, 372(9649), 1541.CrossRefGoogle Scholar
  16. Chakraborty, H. 2008b. The design and analysis aspects of cluster randomized trials. In Statistical advances in the biomedical sciences: Clinical trials, epidemiology, survival analysis, and bioinformatics, ed. A. Biswas, S. Datta, J. Fine, and M. Segal, 67–75. New York, NY: John Wiley and Sons.Google Scholar
  17. Chakraborty, H., J. Moore, W. A. Carlo, T. D. Hartwell, and L. L. Wright. 2009. A simulation based technique to estimate intracluster correlation for a binary variable. Contemp. Clin. Trials, 30(1), 71–80.CrossRefGoogle Scholar
  18. Chakraborty, H., J. Moore, and T. D. Hartwell. 2009. Intracluster correlation adjustments to maintain power in cluster trials for binary outcomes. Contemp. Clin. Trials, 30(5), 473–480.CrossRefGoogle Scholar
  19. Chakraborty, H., and P. K. Sen. 2013. Resampling method to estimate intracluster correlation for clustered binary data. Commun. Stat. Theory Methods, (forthcoming).Google Scholar
  20. Chuang, J.-H., G. Hripcsak, and D. Heitjan. 2002. Design and analysis of controlled trials in naturally clustered environments. J. Am. Med. Inform. Assoc., 9(3), 230–239.CrossRefGoogle Scholar
  21. Cook, J., T. Bruckner, and G. S. MacLennan. 2012. Clustering in surgical trials—Database of intracluster correlations. Trials, 13(2), 1–8.Google Scholar
  22. Cornfield, J. 1978. Randomization by group: A formal analysis. Am. J. Epidemiol., 108, 100–102.CrossRefGoogle Scholar
  23. DerSimonian, R., and N. Laird. 1986. Meta-analysis in clinical trials. Control Clin. Trials, 7(3), 177–88.CrossRefGoogle Scholar
  24. Divine, G. W., J. T. Brown, and L. M. Frazier. 1992. The unit of analysis error in studies about physicians’ patient care behavior. J. Gen. Intern. Med., 7(6): 623–629.CrossRefGoogle Scholar
  25. Donner, A. 1979. The use of correlation and regression in the analysis of family resemblance. Am. J. Epidemiol., 1979;110, 335–342.CrossRefGoogle Scholar
  26. Donner, A. 1986. A review of inference procedures for the intraclass correlation coefficient in the one-way random effects model. Int. Stat. Rev., 54(1), 67–82.MathSciNetzbMATHCrossRefGoogle Scholar
  27. Donner, A. 1998. Some aspects of the design and analysis of cluster randomization trials. J. R. Stat. Soc. Ser. C (Appl. Stat.), 47(1), 95–113.CrossRefGoogle Scholar
  28. Donner, A., N. Birkett, and C. Buck. 1981. Randomization by cluster: Sample size requirements and analysis. Am. J. Epidemiol., 114(6), 906–914.CrossRefGoogle Scholar
  29. Donner, A., K. Brown, and P. Brasher. 1990. A methodological review of non-therapeutic intervention trials employing cluster randomization, 1979–1989. Int. J. Epidemiol., 19, 795–800.CrossRefGoogle Scholar
  30. Donner, A., and A. Donald. 1987. Analysis of data arising from a stratified design with the cluster as unit of randomization. Stat. Med., 6, 43–52.CrossRefGoogle Scholar
  31. Donner, A., and N. Klar. 1994a. Cluster randomisation trials in epidemiology: Theory and application. J. Stat. Plan. Inference, 42, 37–56.zbMATHCrossRefGoogle Scholar
  32. Donner, A., and N. Klar. 1994b. Methods for comparing event rates in intervention studies when the unit of allocation is a cluster. Am. J. Epidemiol., 140, 279–289.CrossRefGoogle Scholar
  33. Donner, A., and N. Klar. 1996. Statistical considerations in the design and analysis of community intervention trials. J. Clin. Epidemiol., 49(4), 435–439.CrossRefGoogle Scholar
  34. Donner, A., and N. Klar. 2000. Design and analysis of cluster randomisation trials in health research. London, UK: Hodder Arnold.Google Scholar
  35. Donner, A., and N. Klar. 2004. Pitfalls of and controversies in cluster randomization trials. Am. J. Public Health, 94(3), 416–422.CrossRefGoogle Scholar
  36. Donner, A., and J. J. Koval. 1980. The estimation of intraclass correlation in the analysis of family data. Biometrics, 36(1), 19–25.zbMATHCrossRefGoogle Scholar
  37. Donner, A., and J. J. Koval. 1983. A note on the accuracy of Fisher’s approximation to the large-sample variance of an intraclass correlation. Commun. Stat. Simul. Comput., 12, 443–449.CrossRefGoogle Scholar
  38. Donner, A., and G. Wells. 2013. A comparison of confidence interval methods for the intraclass correlation coefficient. Biometrics, 42(2), 401–412.MathSciNetzbMATHCrossRefGoogle Scholar
  39. Eldridge, S., and S. Kerry. 2012. A practical guide to cluster randomised trials in health services research. New York, NY: John Wiley and Sons.CrossRefGoogle Scholar
  40. Eldridge, S. M., D. Ashby, G. S. Feder, A. R. Rudnicka, and O. C. Ukoumunne. 2004. Lessons for cluster randomized trials in the twenty-first century: A systematic review of trials in primary care. Clin. Trials, 1(1), 80–90.CrossRefGoogle Scholar
  41. Ennett, S. T., N. S. Tobler, C. L. Ringwalt, and R. L. Flewelling. 1994. How effective is drug abuse resistance education? A meta-analysis of Project DARE outcome evaluations. Am. J. Public Health, 84(9), 1394–401.CrossRefGoogle Scholar
  42. Evans, B. A., Z. Feng, and A. V. Peterson. 2001. 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, 3353–3373.CrossRefGoogle Scholar
  43. Feng, Z., P. Diehr, Y. Yasui, B. Evans, S. Beresford, and T. D. Koepsell. 1999. Explaining community-level variance in group randomized trials. Stat. Med., 18(5), 539–56.CrossRefGoogle Scholar
  44. Fisher, R. 1925. Statistical methods for research workers. Edinburgh, UK: Oliver and Boyd.zbMATHGoogle Scholar
  45. Fleiss, J. L. 1986. Reliability of measurement. In The design and analysis of clinical experiments, 1–32. New York, NY: John Wiley and Sons.zbMATHGoogle Scholar
  46. Fleiss, J. L., and J. Cuzick. 1979. The reliability of dichotomous judgments: Unequal numbers of judges per subject. Appl. Psychol. Meas., 3(4), 537–542.CrossRefGoogle Scholar
  47. Gail, M., D. Byar, T. Pechaceck, and D. Corle. 1992. Aspects of statistical design for the community intervention trial for smoking cessation (COMMIT). Control Clin. Trials, 13, 6–21.CrossRefGoogle Scholar
  48. Gilbody, S., P. Bower, D. Torgerson, and D. Richards. 2008. Cluster randomized trials produced similar results to individually randomized trials in a meta-analysis of enhanced care for depression. J. Clin. Epidemiol., 61(2), 160–168.CrossRefGoogle Scholar
  49. Goldstein, H. 1995. Multilevel statistical models. New York, NY: Edward Arnold; Halstead Press.zbMATHGoogle Scholar
  50. Gulliford, M. C., G. Adams, O. C. Ukoumunne, R. Latinovic, S. Chinn, and M. J. Campbell. 2005. Intraclass correlation coefficient and outcome prevalence are associated in clustered binary data. J. Clin. Epidemiol., 58(3), 246–251.CrossRefGoogle Scholar
  51. Hade, E. M., D. M. Murray, M. L. Pennell, D. Rhoda, E. D. Paskett, V. L. Champion, et al. 2010. Intraclass correlation estimates for cancer screening outcomes: Estimates and applications in the design of group-randomized cancer screening studies. J. Natl. Cancer Inst. Monogr., 2010(40), 97–103.CrossRefGoogle Scholar
  52. Halloran, M. E., C. J. Struchiner, and I. M. Longini. 1997. Study designs for evaluating different efficacy and effectiveness aspects of vaccines. Am. J. Epidemiol., 146(10), 789–803.CrossRefGoogle Scholar
  53. Handlos, L., H. Chakraborty, and P. K. Sen. 2009. Evaluation of cluster randomized trials on maternal and child health research in developing countries. Trop. Med. Int. Health, 14(8), 947–956.CrossRefGoogle Scholar
  54. Hayes, R. J., N. D. E. Alexander, S. Bennett, and S. N. Cousens. 2000. Design and analysis issues in cluster-randomized trials of interventions against infectious diseases. Stat. Methods Med. Res., 9, 95–116.zbMATHCrossRefGoogle Scholar
  55. Hayes, R. J., and S. Bennett. 1999. Simple sample size calculation for cluster-randomized trials. Int. J. Epidemiol. 28(2): 319–26.CrossRefGoogle Scholar
  56. Hedges, L. V., and E. C. Hedberg. 2007. Intraclass correlation values for planning group-randomized trials in education. Educ. Eval. Policy Anal., 29(1), 60–87.CrossRefGoogle Scholar
  57. Hereren, T., and R. D’Agostino. 1987. Robustness of the two independent samples t-test when applied to ordinal scaled data. Stat. Med., 6, 79–90.CrossRefGoogle Scholar
  58. Hewitt, C. E., D. J. Torgerson, and J. N. Miles. 2008. Individual allocation had an advantage over cluster randomization in statistical efficiency in some circumstances. J. Clin. Epidemiol., 61(10), 1004–1008.CrossRefGoogle Scholar
  59. Huber, P. 1981. Robust statistics. New York, NY: Wiley.zbMATHCrossRefGoogle Scholar
  60. Isaakidis, P., and J. P. A. Ioannidis. 2003. Evaluation of cluster randomized controlled trials in Sub-Saharan Africa. Am. J. Epidemiol., 158(9), 921–926.CrossRefGoogle Scholar
  61. Karlin, S., E. Cameron, and P. Williams. 1981. Sibling and parent-offspring correlation estimation with variable family size. Proc. Natl. Acad. Sci. USA, 78(5), 2664–2668.MathSciNetzbMATHCrossRefGoogle Scholar
  62. Kernan, W. N., C. M. Viscoli, R. W. Makuch, L. M. Brass, and R. I. Horwitz. 1999. Stratified randomization for clinical trials. J. Clin. Epidemiol., 52(1), 19–26.CrossRefGoogle Scholar
  63. Kerry, S. M., and J. M. Bland. 1998. Trials which randomize practices 1: How should they be analysed? Family Pract., 15(1), 80–83.CrossRefGoogle Scholar
  64. Killip, S., Z. Mahfoud, and K. Pearce. 2004. What is an intracluster correlation coefficient? Crucial concepts for primary care researchers. Ann. Family Med., 2(3), 204–208.CrossRefGoogle Scholar
  65. Kleinman, J. C. 1973. Proportions with extraneous variance: Single and independent samples. J. Am. Stat. Assoc., 68(341), 46–54.Google Scholar
  66. Kupper, L. L., and J. K. Haseman. 1978. The use of a correlated binomial model for the analysis of certain toxicological experiments. Biometrics, 34(1), 69–76.zbMATHCrossRefGoogle Scholar
  67. Lee, E., and N. Durbin. 1994. Estimation and sample size considerations for clustered binary responses. Stat. Med., 13, 1241–1252.CrossRefGoogle Scholar
  68. Liang, K. Y., and S. L. Zeger. 1986. Longitudinal data analysis using generalized linear models. Biometrika, 73(1), 13–22.MathSciNetzbMATHCrossRefGoogle Scholar
  69. Lipsitz, S. R., N. M. Laird, and T. A. Brennan. 1994. Simple moment estimates of the k-coefficient and its variance. J. R. Stat. Soc. Ser. C, 43(2), 309–323.MathSciNetzbMATHGoogle Scholar
  70. MacLennan, G., C. Ramsay, J. Mollison, K. Campbell, J. Grimshaw, and R. Thomas. 2003. Room for improvement in the reporting ofcluster randomised trials in behaviour change research. New York, NY: Elsevier Science.Google Scholar
  71. Mak, T. K. 1988. Analysing Intraclass Correlation for Dichotomous Variables. J. R. Stat. Soc. Ser. C, 37(3), 344–352.Google Scholar
  72. Maritz, T., and R. Jarrett. 1983. The use of statistics to examine the assiciation between fluoride in drinking water and cancer death rates. Appl. Stat., 32(2), 97–101.CrossRefGoogle Scholar
  73. McCullagh, P., and J. A. Nelder. 1989. Generalized linear models, 2nd ed. London, UK: Chapman and Hall.zbMATHCrossRefGoogle Scholar
  74. McKinlay, S. M., E. J. Stone, and D. M. Zucker. 1989. Research design and analysis issues. Health Educ. Behav., 16(2), 307–313.Google Scholar
  75. Murray, D. M., S. P. Varnell, and J. L. Blitstein. 2004. Design and analysis of group-randomized trials: A review of recent methodological developments. Am. J. Public Health, 94(3), 423–32.CrossRefGoogle Scholar
  76. Nelder, J. A. 1987. Pregibon D. An extended quasi-likelihood function. Biometrika, 74(2), 221–232.MathSciNetzbMATHCrossRefGoogle Scholar
  77. Ochi, Y., and R. L. Prentice. 1984. Likelihood inference in a correlated probit regression model. Biometrika, 71(3), 531–543.MathSciNetzbMATHCrossRefGoogle Scholar
  78. Online intraclass correlation database. n.d. http://stateva.ci.northwestern.edu
  79. Prentice, R. L. 1986. Binary regression using an extended beta-binomial distribution, with discussion of correlation induced by covariate measurement errors. J. Am. Stat. Assoc., 81(394), 321–327.zbMATHCrossRefGoogle Scholar
  80. Puffer, S., D. J. Torgerson, and J. Watson. 2003. Evidence for risk of bias in cluster randomised trials: Review of recent trials published in three general medical journals. Br. Med. J., 327, 1–5.CrossRefGoogle Scholar
  81. Raudenbush, S. W. 1997. Statistical analysis and optimal design for cluster randomized trials. Psychol. Methods, 2(2), 173–185.CrossRefGoogle Scholar
  82. Reading, R., I. Harvey, and M. Mclean. 2000. Cluster randomised trials in maternal and child health: Implications for power and sample size. Arch. Dis. Child., 82(1), 79–83.CrossRefGoogle Scholar
  83. Ridout, M. S., C. G. B. Demetrio, and D. Firth. 1999. Estimating intraclass correlation for binary data. Biometrics, 55(March), 137–148.zbMATHCrossRefGoogle Scholar
  84. Rogers W. 1993. Regression standard errors in clustered samples. Stata Tech. Bull., 13, 19–23.Google Scholar
  85. Schulz, K. F. 1995. Subverting randomization in controlled trials. J. Am. Med. Assoc., 274(18), 1456–1458.CrossRefGoogle Scholar
  86. Simpson, J. M., N. Klar, and A. Donner. 1995. Accounting for cluster randomization: A review of primary prevention trials, 1990 through 1993. Am. J. Public Health, 85(10), 1378–1383.CrossRefGoogle Scholar
  87. Smith, C. 1956. On the estimation of intraclass correlation. Ann. Hum. Genet., 21, 363–373.MathSciNetzbMATHCrossRefGoogle Scholar
  88. Smith, C. 1980a. Estimating genetic correlations. Ann. Hum. Genet., 44, 265–284.MathSciNetzbMATHCrossRefGoogle Scholar
  89. Smith, C. 1980b. Further Remarks on estimating genetic correlations. Ann. Hum. Genet., 44, 95–105.MathSciNetzbMATHCrossRefGoogle Scholar
  90. Spiegelhalter, D. J. 2001. Bayesian methods for cluster randomized trials with continuous responses. Stat. Med., 20(3), 435–52.CrossRefGoogle Scholar
  91. Srivastava, M. S. 1984. Estimation of interclass correlations in familial data. Biometrika, 71(1), 177.MathSciNetzbMATHCrossRefGoogle Scholar
  92. Stiratelli, R., N. Laird, and J. H. Ware. 1984. Random-effects models for serial observations with binary response. Biometrics, 40(4), 961–971.CrossRefGoogle Scholar
  93. Swiger, L. A., W. R. Harvey, D. O. Everson, and K. E. Gregory. 1964. The variance of intraclass correlation involving groups with one observation. Biometrics, 20(4), 818–826.zbMATHCrossRefGoogle Scholar
  94. Tamura, R. N., and S. S. Young. 1987. A stabilized moment estimator for the beta-binomial distribution. Biometrics, 43(4), 813–824.zbMATHCrossRefGoogle Scholar
  95. Thabane, L., L. Mbuagbaw, S. Zhang, Z. Samaan, M. Marcucci, C. Ye, et al. 2013. A tutorial on sensitivity analyses in clinical trials: The what, why, when and how. BMC Med. Res. Methodol., 13(1), 92.CrossRefGoogle Scholar
  96. Thomas, J., and R. Hultquist. 1978. Interval estimation for the unbalanced case of the one-way random effects model. Ann. Stat., 6, 582–587.MathSciNetzbMATHCrossRefGoogle Scholar
  97. Thompson, S. G., S. D. Pyke, and R. J. Hardy. 1997. The design and analysis of paired cluster randomized trials: An application of meta-analysis techniques. Stat. Med., 16(18), 2063–2079.CrossRefGoogle Scholar
  98. Turner, R. M., R. Z. Omar, and S. G. Thompson. 2001. Bayesian methods of analysis for cluster randomized trials with binary outcome data. Stat. Med., 20(3), 453–72.CrossRefGoogle Scholar
  99. Turner, R., A. Prevost, and S. G. Thompson. 2004. Allowing for imprecision of the intracluster correlation coefficient in the design of cluster randomized trials. Stat. Med., 23, 1195–1214.CrossRefGoogle Scholar
  100. Ukoumunne, O. C., M. C. Gulliford, S. Chinn, J. Sterne, and P. Burney. 1999. Methods for evaluating area-wide and organization-based interventions in health and health care: A systematic review. Health Technol. Assess., 3(5), iii–92.Google Scholar
  101. Ware, J. H. 1985. Linear models for the analysis of longitudinal studies. Am. Stat., 39(2), 95–101.Google Scholar
  102. White, H. 1980. A heteroskedasticity-consistent covariance matrix estimator and a direct test for heteroskedasticity. Econometrica, 48(4), 817–838.MathSciNetzbMATHCrossRefGoogle Scholar
  103. Whiting-O’Keefe, Q. E., C. Henke, and D. W. Simborg. 1984. Choosing the correct unit of analysis in medical care experiments. Med. Care. 22(12), 1101–1114.CrossRefGoogle Scholar
  104. Williams, D. A. 1982. Extra-binomial variation in logistic linear models. J. R. Stat. Soc. Ser. C, 31(2), 144–148.zbMATHGoogle Scholar
  105. Wolfinger, R., and M. O’Connell. 1993. Generalized linear mixed models: A pseudo-likelihood approach. J. Stat. Comput. Simul., 48, 233–243.zbMATHCrossRefGoogle Scholar
  106. Wu, S., C. M. Crespi, and W. K. Wong. 2012. Comparison of methods for estimating the intraclass correlation coefficient for binary responses in cancer prevention cluster randomized trials. Contemp. Clin. Trials, 33(5), 869–880.CrossRefGoogle Scholar
  107. Yamamoto, E., and T. Yanagimoto. 1992. Moment estimators for the binomial distribution. J. Appl. Stat., 19, 273–283.CrossRefGoogle Scholar
  108. Zeger, S., and K. Liang. 1992. An overview of methods for the analysis of longitudinal data. Stat. Med., 11, 825–839.CrossRefGoogle Scholar

Copyright information

© Grace Scientific Publishing 2015

Authors and Affiliations

  1. 1.Department of Epidemiology and Biostatistics, Arnold School of Public HealthThe University of South CarolinaColumbiaUSA

Personalised recommendations