Intended for healthcare professionals

Endgames Statistical Question

Randomised controlled trials: internal versus external validity

BMJ 2014; 348 doi: (Published 28 February 2014) Cite this as: BMJ 2014;348:g1742
  1. Philip Sedgwick, reader in medical statistics and medical education
  1. 1Centre for Medical and Healthcare Education, St George’s, University of London, London, UK
  1. p.sedgwick{at}

Researchers investigated the effectiveness of melatonin in treating severe sleep problems in children with neurodevelopmental disorders. A double blind randomised placebo controlled study design was used. The intervention was immediate release melatonin capsules administered 45 minutes before the child’s bedtime for a period of 12 weeks. Participants were 146 children aged 3 to 15 years 8 months. The trial was a multicentre one, with children recruited from 19 hospitals across England and Wales. The children had a severe sleep problem that had not responded to standardised sleep behaviour advice provided to parents four to six weeks before randomisation. The children were randomised to melatonin (n=70) or placebo (n=76).1

The outcome measures included subjective (as assessed from sleep diaries completed by the parents) and objective (as recorded by actigraphy) measures of sleep. The proportion of randomised participants who completed follow-up was 94% (66/70) for melatonin and 92% (70/76) for placebo. An intention to treat analysis was used to compare treatment groups in outcome. The researchers reported that children gained little additional sleep on melatonin compared with placebo. However, the children receiving melatonin fell asleep significantly faster and their waking times were earlier.

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

  • a) The multicentre trial design promoted external validity

  • b) The random allocation of patients to treatment promoted internal validity …

View Full Text

Log in

Log in through your institution


* For online subscription