Skip to main content

Advertisement

Comparative evaluation of the stepped wedge design efficiency

Article metrics

  • 667 Accesses

The cluster randomised trial (CRT) design is widely used to evaluate interventions targeted at the cluster level and helps alleviate contamination within clusters. CRTs usually require large sample sizes, although matched pair CRTs can limit this problem. The stepped wedge design (SWD) extends CRTs, in cases where it is expected that the intervention will do more good than harm and/or, for logistical, practical or financial reasons, it is impossible to deliver the intervention simultaneously to all clusters. In a SWD different clusters cross over from control to treatment unidirectionally at different time points. Clusters receive the intervention sequentially over a number of time periods. All clusters are initially assigned to the control condition. At successive, randomly determined times some clusters begin the treatment and the response is measured. Eventually, all receive the treatment.

The literature on SWD is not extensive and thus its relative performance (eg against standard or matched pair CRTs) has not been investigated adequately. The SWD has the potential to reduce the sample size substantially and could be a viable alternative to CRTs provided that the relevant assumptions hold. We perform simulation studies, under different scenarios (eg varying the number of clusters, time periods within the SWD and cluster size, considering both repeated cross-sectional and longitudinal design, for continuous, binary and count data) to identify situations in which the SWD could offer substantial advantages in terms of sample size, without incurring additional costs due to increase in the total length of time to run a trial.

Author information

Correspondence to Gianluca Baio.

Rights and permissions

This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Reprints and Permissions

About this article

Keywords

  • Public Health
  • Simulation Study
  • Large Sample Size
  • Cluster Size
  • Additional Cost

Comments

By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate. Please note that comments may be removed without notice if they are flagged by another user or do not comply with our community guidelines.