Endgames Statistical Question

Treatment allocation in trials: block randomisation

BMJ 2014; 348 (Published 28 March 2014) Cite this as: BMJ 2014;348:g2409
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}sgul.ac.uk

Researchers investigated the efficacy of nicotine patches in pregnant smokers. A randomised, double blind, placebo controlled, parallel group, multicentre trial study design was used. The intervention was 16 hour nicotine patches administered until the time of delivery. Participants were pregnant smokers aged over 18 years, whose babies were between 12 and 20 weeks’ gestation, and who smoked at least five cigarettes a day. In total, 402 women were recruited from 23 maternity wards throughout France. Participants were allocated to treatment (203 to nicotine patches and 199 to placebo patches) by block randomisation, using a block size of four.1

The primary outcome measures included complete abstinence until delivery and birth weight. Complete abstinence was achieved by 5.5% (n=11) of women in the nicotine patch group and 5.1% (n=10) in the placebo group (odds ratio 1.08, 95% confidence interval 0.45 to 2.60). The mean birth weight was 3065 g (standard error 44 g) in the nicotine patch group and 3015 g (44 g) in the placebo group (P=0.41). The researchers concluded that the nicotine patches did not significantly increase smoking cessation rates or birth weights.

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

• a) The objective of block randomisation was to ensure similar numbers of patients in the treatment groups

• b) Participants were allocated to treatment four at a time in an alternate order, with the order decided at random

• c) Block randomisation ensured a similar distribution of baseline characteristics in each treatment group

• d) Maternity wards were allocated to a treatment, with women receiving the treatment that their ward had been allocated

• e) Upon recruitment, each participant had an equal probability of being allocated to the intervention group or control group

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

The aim of …

View Full Text