Confidence intervals and statistical significance: rules of thumbBMJ 2012; 345 doi: https://doi.org/10.1136/bmj.e4960 (Published 25 July 2012) Cite this as: BMJ 2012;345:e4960
- Philip Sedgwick, reader in medical statistics and medical education
- 1Centre for Medical and Healthcare Education, St George’s, University of London, Tooting, London, UK
Researchers compared the effectiveness of cryotherapy with that of salicylic acid for treating plantar warts. A randomised controlled trial was performed. Participants were eligible if aged 12 years or over. Those randomised to cryotherapy had liquid nitrogen delivered by a healthcare professional, with a maximum of four treatments, 2-3 weeks apart. Participants randomised to 50% salicylic acid (Verrugon) treated themselves daily for a maximum of eight weeks.1
The primary outcome was complete clearance of all plantar warts at 12 weeks, as confirmed by inspection of digital photographs by two assessors who were blind to treatment allocation. Secondary outcomes included patients’ self reported number of days until clearance of plantar warts in the six months after randomisation. The proportion of participants with complete clearance of plantar warts at 12 weeks was higher in the salicylic group (17 of 119 (14.29%) versus 15 of 110 (13.64%); difference 0.65% (95% confidence interval –8.33 to 9.63)). The hazard ratio for self reported time to clearance of plantar warts in the six months after randomisation when salicylic acid was compared with cryotherapy was 0.8 (0.51 to 1.25).
Which of the following statements, if any, can be concluded?
a) The percentage difference between treatment groups in …