Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Nov 15;7(11):e017151.
doi: 10.1136/bmjopen-2017-017151.

Unequal cluster sizes in stepped-wedge cluster randomised trials: a systematic review

Caroline Kristunas  1 , Tom Morris  2 , Laura Gray  1
Affiliations

Unequal cluster sizes in stepped-wedge cluster randomised trials: a systematic review

Caroline Kristunas et al. BMJ Open. .

Abstract

Objectives: To investigate the extent to which cluster sizes vary in stepped-wedge cluster randomised trials (SW-CRT) and whether any variability is accounted for during the sample size calculation and analysis of these trials.

Setting: Any, not limited to healthcare settings.

Participants: Any taking part in an SW-CRT published up to March 2016.

Primary and secondary outcome measures: The primary outcome is the variability in cluster sizes, measured by the coefficient of variation (CV) in cluster size. Secondary outcomes include the difference between the cluster sizes assumed during the sample size calculation and those observed during the trial, any reported variability in cluster sizes and whether the methods of sample size calculation and methods of analysis accounted for any variability in cluster sizes.

Results: Of the 101 included SW-CRTs, 48% mentioned that the included clusters were known to vary in size, yet only 13% of these accounted for this during the calculation of the sample size. However, 69% of the trials did use a method of analysis appropriate for when clusters vary in size. Full trial reports were available for 53 trials. The CV was calculated for 23 of these: the median CV was 0.41 (IQR: 0.22-0.52). Actual cluster sizes could be compared with those assumed during the sample size calculation for 14 (26%) of the trial reports; the cluster sizes were between 29% and 480% of that which had been assumed.

Conclusions: Cluster sizes often vary in SW-CRTs. Reporting of SW-CRTs also remains suboptimal. The effect of unequal cluster sizes on the statistical power of SW-CRTs needs further exploration and methods appropriate to studies with unequal cluster sizes need to be employed.

Keywords: cluster randomised trial; stepped-wedge trial; systematic review.

PubMed Disclaimer

Conflict of interest statement

Competing interests: None declared.

Figures

Figure 1
Figure 1
Schematic representation of a stepped-wedge cluster randomised trial with four steps. The white areas represent control periods and the shaded areas represent intervention periods.
Figure 2
Figure 2
Flow chart showing the studies identified by the systematic review.
See this image and copyright information in PMC

References

    1. Eldridge S, Kerry S. A Practical Guide to Cluster Randomised Trials in Health Services Research. US: John Wiley & Sons Inc, 2012.
    1. Hemming K, Haines TP, Chilton PJ, et al. . The stepped wedge cluster randomised trial: rationale, design, analysis, and reporting. BMJ 2015;350:h391 10.1136/bmj.h391 - DOI - PubMed
    1. Beard E, Lewis JJ, Copas A, et al. . Stepped wedge randomised controlled trials: systematic review of studies published between 2010 and 2014. Trials 2015;16:1–14. 10.1186/s13063-015-0839-2 - DOI - PMC - PubMed
    1. Lauer SA, Kleinman KP, Reich NG. The effect of cluster size variability on statistical power in cluster-randomized trials. PLoS One 2015;10:e0119074 10.1371/journal.pone.0119074 - DOI - PMC - PubMed
    1. Eldridge SM, Ashby D, Kerry S. Sample size for cluster randomized trials: effect of coefficient of variation of cluster size and analysis method. Int J Epidemiol 2006;35:1292–300. 10.1093/ije/dyl129 - DOI - PubMed

Publication types

LinkOut - more resources