Endgames Statistical Question

Cluster sampling

BMJ 2014; 348 doi: https://doi.org/10.1136/bmj.g1215 (Published 31 January 2014) Cite this as: BMJ 2014;348:g1215
  1. Philip Sedgwick, reader in medical statistics and medical education1
  1. 1Centre for Medical and Healthcare Education, St George’s, University of London, London, UK
  1. p.sedgwick{at}sgul.ac.uk

Researchers investigated the effectiveness of providing smoking cessation support to adult smokers admitted to hospital. A cluster randomised controlled trial study design was used. The intervention comprised systematic smoking ascertainment and default provision of behavioural support and cessation pharmacotherapy for the duration of the hospital stay, with follow-up and referral to community services after discharge. Control treatment comprised usual care, with cessation support delivered at the initiative and discretion of clinical staff.1

Participants were recruited using cluster sampling. Smokers and recent ex-smokers admitted to 18 acute medical wards in one large UK teaching hospital between 11 October 2010 and 9 August 2011 were invited to take part. In total, 493 patients were recruited. Wards were allocated to treatment using random allocation, stratified by the number of discharges per week. Nine wards were allocated to each treatment, resulting in 264 patients receiving the intervention and 229 the control treatment.

The primary outcome measure was smoking cessation at four weeks, validated by measuring exhaled carbon monoxide. A greater proportion of the intervention group achieved smoking cessation at four weeks compared with controls (adjusted odds ratio 2.10, 95% confidence interval 0.96 to 4.61; P=0.06). It was concluded that improvements in smoking cessation among smokers and recent ex-smokers admitted to hospital can be achieved by systematic ascertainment and delivery of cessation support in secondary care.

Which of the following statements, if any, are true?

  • a) Cluster sampling involved recruiting a random sample of adult patients from each …

View Full Text

Log in

Log in through your institution


* For online subscription