Research Methods & Reporting
How to design efficient cluster randomised trials
BMJ 2017; 358 doi: https://doi.org/10.1136/bmj.j3064 (Published 14 July 2017) Cite this as: BMJ 2017;358:j3064- K Hemming, senior lecturer1,
- S Eldridge, professor of biostatistics2,
- G Forbes, statistician2,
- C Weijer, professor3,
- M Taljaard, senior scientist45
- 1Institute of Applied Health Research, University of Birmingham, Birmingham B15 2TT, UK
- 2Pragmatic Clinical Trials Unit, Centre for Primary Care and Public Health, Queen Marys University, London, UK
- 3Rotman Institute of Philosophy, Western University, London N6A 5B8, Canada
- 4Clinical Epidemiology Program, Ottawa Hospital Research Institute, 1053 Carling Avenue, Ottawa, Ontario, K1Y4E9, Canada
- 5School of Epidemiology, Public Health and Preventive Medicine, University of Ottawa, Ottawa, Ontario, Canada
- Correspondence to: K Hemming k.hemming{at}bham.ac.uk
- Accepted 5 June 2017
Summary points
Cluster randomised trials have diminishing returns in power and precision as cluster size increases
In some situations a small increase in the number of clusters can lead to …