ABSTRACT
A cluster randomized trial (CRT) randomizes groups of individuals to each intervention of a trial rather than individuals. The clusters used in CRTs vary widely and range in size from families to entire communities. CRTs have become increasingly used in health services research because they are ideally suited to address issues related to policy, practice, and healthcare organizations with groups defined by social organizations or geographical areas such as schools, medical clinics, hospitals, churches, or communities. A critical feature of cluster randomization trials is the dependency among subjects within the same cluster. Outcomes for individuals within a cluster are likely to be more similar to each other than those for individuals from other clusters due to the following possible reasons. The degree of similarity or correlation within the same cluster is typically measured by an intracluster correlation coefficient. Continuous outcomes frequently occur in cluster randomized trials.
