Intended for healthcare professionals

Endgames Statistical Question

Cluster randomised controlled trials

BMJ 2012; 345 doi: (Published 11 July 2012) Cite this as: BMJ 2012;345:e4654
  1. Philip Sedgwick, senior lecturer in medical statistics
  1. 1Centre for Medical and Healthcare Education, St George’s, University of London, Tooting, London, UK
  1. p.sedgwick{at}

Researchers investigated whether a systematic approach to the treatment of pain reduced agitation in people with moderate to severe dementia living in nursing homes. A cluster randomised controlled trial study design was used. The intervention comprised a stepwise protocol for the treatment of pain for eight weeks, with additional follow-up lasting four weeks from the end of treatment. The control group received the usual treatment and care.1

A sample of 352 residents living in 60 nursing home units across five municipalities of western Norway was identified. Each nursing home unit was independent, with no crossover of staff, and defined as a natural cluster for the purpose of the trial. Residents were eligible if they were aged 65 or older and had moderate to severe dementia and clinically significant behavioural disturbances. In total, 175 residents living in 33 clusters were randomised to intervention, and 177 residents living in 27 clusters were randomised to control. The primary outcome was agitation as measured on the Cohen-Mansfield agitation inventory. The researchers reported that the systematic approach to …

View Full Text

Log in

Log in through your institution


* For online subscription