Although PCTs do not necessarily require a specific statistical design approach, both the kinds of questions PCTs are designed to answer and the settings in which they take place may favor certain approaches, such as cluster randomization. The nature of the interventions PCTs seek to test, which may involve healthcare delivery changes, might be better implemented through randomization at the practice, clinic, or even hospital level.

In the following sections, we examine key considerations in study design and analysis for PCTs.

Watch the video module: What Is an Example of How to Choose a Study Design?

Three Kinds of Randomized Trials

A key design factor for PCTs is the unit of randomization. Here we outline 3 kinds of randomized trials:

In traditional RCTs, the unit of randomization is generally the individual trial participant, and each participant is randomly assigned to a study condition, where the study condition is typically an experimental intervention, a comparator therapy, or a placebo. There is no interaction among participants after randomization. Most drug trials are traditional RCTs.

In individually randomized group treatment (IRGT) trials, like traditional RCTs, the unit of randomization is the individual trial participant, and each participant is randomly assigned to a study condition. However, there is interaction among trial participants after randomization in one or more of the study conditions. Many surgical trials and behavioral trials are IRGT trials. These trial designs are sometimes called "partially nested" or "partially clustered" designs.

In cluster randomized trials (CRTs), randomization takes place at the level of the clinician, practice, hospital, healthcare system, city block, or other unit that comprises multiple patients or other participants. Each group, or “cluster,” is randomly assigned to a study condition, and there is interaction among members of the same group before and after randomization. Many trials conducted in communities, work sites, schools, and other settings are CRTs. CRTs are sometimes called "group randomized trials" or "community trials." In CRTs, the intervention can be applied at the individual level or the cluster level, and the outcome measurements can be taken at the individual level or the cluster level.

Case Example: Unit of Randomization vs Unit of Measurement

The Time to Reduce Mortality in End-Stage Renal Disease (TiME) trial, an NIH Collaboratory Trial, offers an example of the difference between the unit of randomization and the unit of measure typical of CRTs. In the TiME trial, dialysis clinics providing care to patients with end-stage renal disease were randomly assigned to provide 1 of 2 interventions: an "extended" period of hemodialysis or standard care. The trial was designed to evaluate whether the extended period of dialysis would be associated with better survival and quality-of-life outcomes. The researchers chose clinic-level randomization over patient-level randomization “to facilitate implementation of the intervention and minimize contamination” (Dember et al 2019). (See Choosing Between Cluster and Individual Randomization for more details.) Thus, the unit of randomization in the TiME trial was the dialysis clinic, but the measurements of interest were the outcomes of individual patients.