Endgames Statistical Question

Non-inferiority trials

BMJ 2011; 342 doi: https://doi.org/10.1136/bmj.d3253 (Published 01 June 2011) Cite this as: BMJ 2011;342:d3253
  1. Philip Sedgwick, senior lecturer in medical statistics
  1. 1Section of Medical and Healthcare Education, St George’s, University of London, Tooting, London, UK
  1. p.sedgwick{at}sgul.ac.uk

Researchers investigated the efficacy and safety of oral pristinamycin for the treatment of erysipelas in patients admitted to hospital. A multicentre, randomised controlled non-inferiority trial was performed.1 The control treatment was penicillin, the standard treatment for erysipelas in adults. Penicillin is given intravenously until body temperature returns to normal, after which it is given orally. Unfortunately, intravenous treatment is painful, time consuming, requires hospital admission, and not uncommonly has side effects. If pristinamycin could be shown to be as effective as penicillin it could be used as first line treatment, with the advantage that it is given orally.

The primary end point was proportion of adults cured of erysipelas at follow-up (days 25-45). A non-inferiority margin of 10% was proposed. In total, 139 adults were randomised to oral pristinamycin and 150 to the standard treatment of penicillin. Using an intention to treat analysis, the cure rate at follow-up was 65% for pristinamycin and 53% for penicillin (difference favouring …

View Full Text

Log in

Log in through your institution


* For online subscription