Intended for healthcare professionals

Endgames Statistical Question

Units of analysis

BMJ 2013; 346 doi: (Published 05 April 2013) Cite this as: BMJ 2013;346:f2128
  1. Philip Sedgwick, reader in medical statistics and medical education
  1. 1Centre for Medical and Healthcare Education, St George’s, University of London, Tooting, London, UK
  1. p.sedgwick{at}

Researchers assessed the effectiveness of a physical activity programme during one school year on the physical and psychological health of young schoolchildren. A cluster randomised controlled trial design was used. The physical activity programme consisted of three existing physical education lessons each week supplemented by a further two lessons, daily short activity breaks, and physical activity homework. Children in the control group received only the three existing physical education lessons each week.1

In total, 28 classes at 15 elementary schools in Switzerland were recruited. Classes were randomly assigned to treatment in a 4:3 ratio; 16 classes at nine schools were assigned to the intervention and 12 classes at six schools were assigned to the control. There were 297 children allocated to intervention and 205 to control.

Primary outcome measures included for each child the change between baseline and follow-up in body fat, aerobic fitness, physical activity, and quality of life measures. The researchers reported that the school based multicomponent physical activity intervention improved physical activity …

View Full Text

Log in

Log in through your institution


* For online subscription