Endgames Statistical Question

Quantifying treatment effects in randomised controlled trials

BMJ 2015; 350 doi: https://doi.org/10.1136/bmj.h420 (Published 23 January 2015) Cite this as: BMJ 2015;350:h420
  1. Philip Sedgwick, reader in medical statistics and medical education1
  1. 1Institute for Medical and Biomedical Education, St George’s, University of London, London, UK
  1. p.sedgwick{at}sgul.ac.uk

Researchers investigated the efficacy of varenicline in helping users of smokeless tobacco to quit. Varenicline is a licensed cigarette smoking cessation aid. A randomised double blind placebo controlled trial was performed. The intervention was varenicline 1 mg twice daily delivered for 12 weeks, with 14 weeks’ follow-up. Participants were users of smokeless tobacco who wished to quit, aged 18 years or more. In total, 431 participants were recruited and randomised to varenicline (n=213) or placebo (n=218). All participants were offered brief behavioural support or counselling at the discretion of the investigators.1

The primary endpoint was continuous abstinence for four weeks at the end of treatment (weeks 9-12) confirmed by cotinine concentration. A higher rate of abstinence was reported in the varenicline group than in the placebo group (59% v 39%; unadjusted relative risk 1.51, 95% confidence interval 1.23 to 1.84; number needed to treat 5). A higher proportion of the varenicline group reported an adverse event compared with the placebo group (79% v 58%; number needed to harm 4.76). The researchers concluded that varenicline could help people to give up smokeless tobacco and that it had an acceptable safety profile.

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

  • a) The absolute increase in abstinence of 20% for varenicline compared with placebo represented the treatment effect

  • b) The absolute increase in abstinence of 20% for varenicline compared with placebo is referred to as the absolute risk increase

  • c) The relative risk of abstinence for varenicline compared with placebo represented a relative increase of 51% in risk

  • d) The number needed to harm indicates how many participants need to be treated with varenicline for one more patient to experience an adverse event compared with receiving placebo


Statements a, c, and d are true, whereas b is false.

Smokers sometimes use …

View Full Text

Sign in

Log in through your institution

Free trial

Register for a free trial to thebmj.com to receive unlimited access to all content on thebmj.com for 14 days.
Sign up for a free trial