Cluster randomization is commonly selected for PCTs, because individual-level randomization can raise practical implementation challenges and because outcomes within clusters tend to be correlated. There is an extensive literature on the inefficiency of simple (or “parallel”) cluster randomization compared to individual-level randomization and approaches to accounting for this inefficiency in terms of sample size (Donner et al 1981; Hsieh 1988; Donner 1992; Donner and Klar 1996; Campbell et al 2001).

Modified CRT designs, such as cluster-crossover trials, may reduce the required sample size and may be particularly feasible in PCTs in healthcare systems with EHRs. In this section, we describe cluster-crossover trials and their implications for statistical power and sample size calculations.

Inefficiency and Imbalance in Parallel-Arm CRTs

It is well known that parallel-arm CRTs have less statistical power than individual-level RCTs because of correlation within clusters. Specifically, in a trial designed to determine whether there is a significant difference between interventions A and B on response Y, randomization at the cluster level to either A or B would require a larger sample size to obtain the same statistical power as randomization at the individual level. The magnitude of loss of statistical power is related to the cluster size, the balance of cluster sizes (that is, whether there is variability in cluster sizes), and the correlation of individual-level outcomes within the clusters.

For a given sample size, statistical power increases as the number of clusters increases. This makes intuitive sense, in that as the number of clusters increases, the size of the clusters decreases toward 1, or individual-level randomization. Moreover, as the cluster sizes become more imbalanced, statistical power decreases (Eldridge et al 2009). Also, as correlation within a given cluster increases, power decreases. If there were no intracluster correlation, the power would be the same as with individual-level randomization.

Inefficiency is not the only problem with simple CRT designs. Another challenge is the potential for imbalance in baseline factors, especially with large clusters. For example, in study designs that involve clustering at the clinic level, individual clinics may differ in the size and demographic characteristics of their patient populations. These challenges may be overcome by adding a crossover, or a switch to the other intervention, within cluster during randomization.

Cluster Designs With Crossover

In a cluster-crossover trial, each cluster is randomly assigned to a study condition at the beginning of the study and, after a certain period of time, switches (or crosses over) to the other study condition. Timing the crossover to occur approximately halfway through the study achieves balance between the study conditions, including balance on baseline factors.

A cluster-crossover trial is only feasible if the intervention can be turned off and on without “learning,” such that residual practices are not carried over from the precrossover period to the postcrossover period. A carryover effect would cause contamination between the study conditions. Implementing a washout period after the crossover, during which the data from the clusters are discarded, may help to prevent contamination, though washout periods are not always feasible. For example, in a device trial in which hospitals are randomly assigned to the device intervention or usual care, and in which the outcome of interest is patient survival, a carryover effect may occur despite a washout period due to the time sequence of other potential confounding treatments (for example, a new protocol introduced into the system that improves survival midway through the trial). However, there would likely be a balance of these time effects across the study conditions.

When a cluster-crossover design is feasible, it is statistically more efficient than individual-level randomization in certain situations. Nonetheless, we do not advocate the cluster-crossover approach over individual-level randomization, because of challenges with feasibility (such as turning the intervention on and off) and carryover effects. Rather, a cluster-crossover design can be a viable alternative to simple cluster randomization. The efficiency gained with a cluster-crossover design is like that gained from a paired t test over an independent t test. More power is gained as the between-period correlation within cluster increases (Li et al 2019). Furthermore, when the precrossover and postcrossover periods are balanced with the same number of clusters in each condition, statistical power may increase. As the periods become less balanced, power decreases and the study design becomes more like a simple cluster randomized design.

Cluster Designs With Partial Crossover

If an intervention cannot be turned off and on, another simple alternative is to collect data from all clusters during a baseline period before the intervention is introduced, then assign half of the clusters to the intervention and continue to collect data—in other words, a parallel CRT with a baseline period (Hooper et al 2018; Lee et al 2025). This approach involving an untreated baseline period followed by parallel cluster randomization has statistical advantages because data are available from some clusters to efficiently estimate a within-cluster effect without the potential for “learning” contamination, or carryover effect, that could occur with cluster-crossover designs. Moreover, if outcome data are already being collected through the EHR or medical billing claims, this design is more powerful than a simple CRT design without cost to the study, because the data are already available and easily obtained. A limitation of the design is that not all clusters receive the intervention, unlike other designs such as the stepped-wedge trial. (See the Stepped-Wedge Designs section of this chapter.)

Next Steps

Implementing new cluster-crossover designs would be easier if sample size calculators were available that are simpler than currently available simulation approaches. Li et al (2019) developed sample size calculations for 2-period cluster-crossover designs. There is a need for extensions beyond this standard design.