For healthcare professionals only

Endgames Statistical Question

“n of 1” trials

BMJ 2012; 344 doi: (Published 09 February 2012) Cite this as: BMJ 2012;344:e844
  1. Philip Sedgwick, senior lecturer in medical statistics
  1. 1Centre for Medical and Healthcare Education, St George’s, University of London, Tooting, London, UK
  1. p.sedgwick{at}

Researchers investigated whether paracetamol was as effective as non-steroidal anti-inflammatory drugs (NSAIDs) in the treatment of pain and disability related to osteoarthritis of the hip or knee. A series of double blind, randomised “n of 1” controlled trials was performed. Each drug was taken for two weeks, administered for a maximum of five cycles. Thirteen patients in primary care who had regularly been using NSAIDS were selected. Patients received the same type of NSAID and in the same dosage, if possible, as they were taking before the start of the study. Outcome measures included severity of complaints of pain, stiffness, and limitations in daily functioning, together with satisfaction with drugs and side effects.1

Seven patients completed the study, and it was recommended that six of these change to paracetamol. All the other patients continued with NSAIDs. Three months after the study finished, of the six patients for whom a change to paracetamol was recommended, four were taking NSAIDs for practical reasons or because of a perceived lack of efficacy of paracetamol. The authors concluded that n of 1 trials can be used to investigate the …

View Full Text

Log in

Log in through your institution


* For online subscription