Cluster-Randomized Experiment

A Cluster-Randomized Experiment is a randomized experiment that is a cluster-level assignment experiment.

• AKA: GRT, Group Randomized Trial.
• Context:
  • It can range from being a Parallel Cluster Randomized Experiment to being a Repeated Measures Cluster Randomized Experiment (such as a Crossover Cluster Randomized Experiment or a Stepped Wedge Cluster Randomized Trial).
  • It can be designed by a Cluster Randomized Experiment Design Task.
  • It can be analyzed by a Cluster Randomized Experiment Evaluation Task.
  • It can range from being a One-Factor Cluster Randomized Experiment to being a Two-Factor Cluster Randomized Experiment to being a Many-Factor Cluster Randomized Experiment.
  • It can be Group-level Placebo-Treatment Randomized Experiment.
  • It can range from being a Simple Cluster Randomized Experiment to being a Complex Cluster Randomized Experiment.
  • It can range from being a Therapeutic Treatment Cluster Randomized Experiment to being a Preventative Treatment Cluster Randomized Experiment.
  • …
• Example(s):
  • a Randomized eEPC Predictor Lift Analysis Experiment.
  • a Cluster Randomized Experiment Without Controls.
  • …
• Counter-Example(s):
  • a Subject-level Randomized Experiment.
  • a Randomized Crossover Experiment.
  • an Observational Study, such as a Prospective Cohort Study.
• See: Experiment Cohort, Treatment Group, Placebo Group.

---

---

References

2013

• http://en.wikipedia.org/wiki/Randomized_controlled_trial#By_study_design
  • … Cluster – pre-existing groups of participants (e.g., villages, schools) are randomly selected to receive (or not receive) an intervention. …

    … An analysis of the 616 RCTs indexed in PubMed during December 2006 found that 78% were parallel-group trials, 16% were crossover, 2% were split-body, 2% were cluster, and 2% were factorial.

• http://en.wikipedia.org/wiki/Cluster_randomised_controlled_trial
  • A cluster randomised controlled trial is a type of randomised controlled trial in which groups of subjects (as opposed to individual subjects) are randomised. Cluster randomised controlled trials are also known as cluster randomised trials, group-randomised trials, and place-randomized trials.

    A 2004 bibliometric study documented an increasing number of publications in the medical literature on cluster randomised controlled trials since the 1980s. Advantages of cluster randomised controlled trials over individually randomised controlled trials include the ability to study interventions that cannot be directed toward selected individuals (e.g., a radio show about lifestyle changes) and the ability to control for "contamination" across individuals (e.g., one individual's changing behaviors may influence another individual to do so).

    Disadvantages compared with individually randomised controlled trials include greater complexity in design and analysis, and a requirement for more participants to obtain the same statistical power. Specifically, the cluster randomised designs introduce dependence (or clustering) between individual units sampled. An example would be an educational intervention in which schools are randomised to one of several new teaching methods. When comparing differences in outcome achieved under the new methods, researchers must account for the fact that two students sampled from a single school are more likely to be similar (in terms of outcomes) than two students sampled from different schools. Multilevel or similar statistical models are typically used to correct for this non-independence.

2008

• (Brown, Wang, et al., 2008) ⇒ C. Hendricks Brown, Wei Wang, Sheppard G Kellam, Bengt O. Muthén, Hanno Petras, Peter Toyinbo, Jeanne Poduska, Nicholas Ialongo, Peter A Wyman, Patricia Chamberlain, and [The Prevention Science and Methodology Group]]. (2008). “Methods for Testing Theory and Evaluating Impact in Randomized Field Trials: Intent-to-treat Analyses for Integrating the Perspectives of Person, Place, and Time.” In: Drug and Alcohol Dependence Journal, 95. doi:10.1016/j.drugalcdep.2007.11.013

2006

• (Patton, Bond et al., 2006) ⇒ George C. Patton, Lyndal Bond, John B. Carlin, Lyndal Thomas, Helen Butler, Sara Glover, Richard Catalano, and Glenn Bowes. (2006). “Promoting social inclusion in schools: a group-randomized trial of effects on student health risk behavior and well-being.” In: American Journal of Public Health, 96(9).

2004

• (Murray et al., 2004) ⇒ David M. Murray, Sherri P. Varnell, and Jonathan L. Blitstein. (2004). “Design and Analysis of Group-randomized Trials: A Review of Recent Methodological Developments."
  • QUOTE: Group-randomized trials (GRTs) are comparative studies designed to evaluate interventions that operate at a group level, manipulate the physical or social environment, or cannot be delivered to individuals.1 Examples include school-, worksite-, and community-based studies designed to improve the health of students, employees, and residents, respectively. Just as the randomized clinical trial (RCT) is the gold standard in public health and medicine when allocation of individual participants is possible, the GRT is the gold standard when allocation of identifiable groups is necessary.

2000

• (Donner & Klar, 2000) ⇒ Allan Donner, and Neil Klar. (2000). “Design and Analysis of Cluster Randomization Trials in Health Research.." Wiley. ISBN:0470711000
  • QUOTE: A cluster randomization trial is one in which intact social units, or clusters of individuals, are randomized to different intervention groups. Trials randomizing clusters have become particularly widespread in the evaluation of non-therapeutic interventions, including lifestyle modification, educational programmes and innovations in the provision of health care.

1998

• (Murray, 1998) ⇒ David Murray. (1998). “Design and Analysis of Group Randomized Trials." Oxford University Press. ISBN:0195120361
  • QUOTE: Group-randomized trials are comparative studies in which (1) the units of assignment are identifiable groups and (2) the units of observation are members of those groups. In this context, an identifiable group refers quite broadly to any group that is not constituted at random, so that there are some physical, geographic, social, or other connections among its members.

1994

• (Donner & Klar, 1994) ⇒ Allan Donner, and Neil Klar. (1994). “Cluster Randomization Trials in Epidemiology: Theory and Application." Elsevier. doi:10.1016/0378-3758(94)90188-0
  • QUOTE: It is becoming increasingly common for epidemiologists to consider randomizing intact clusters (e.g. families, schools, communities) rather than individuals in experimental trials. Reasons are diverse, but include administrative convenience, a desire to reduce the effect of treatment contamination and the need to avoid ethical issues which might otherwise arise. Dependencies among cluster members typical of such designs must be considered when determining sample size and analyzing the resulting data. Well-known methods such as generalized least squares can be used to analyze continuous outcome data, while methods for the analysis of binary outcome data and correlated failure time data are in the development stage. The purpose of this paper is to review methods used in the design and analysis of cluster randomization trials applied in health sciences research.

---