Intended for healthcare professionals

Endgames Statistical Question

What is significance?

BMJ 2015; 350 doi: (Published 26 June 2015) Cite this as: BMJ 2015;350:h3475
  1. Philip Sedgwick, reader in medical statistics and medical education
  1. 1Institute for Medical and Biomedical Education, St George’s, University of London, London, UK
  1. Correspondence to: P Sedgwick p.sedgwick{at}

The effects of pelvic floor muscle training on pelvic floor symptoms were investigated using a randomised controlled trial. The intervention consisted of pelvic floor muscle training combined with home exercises. The control intervention consisted of watchful waiting. The length of follow-up was three months. The participants were women recruited from a primary care population, aged 55 years or more, who had symptomatic mild pelvic organ prolapse.1

The primary outcome was the change in bladder, bowel, and pelvic floor symptoms at follow-up from baseline as measured by the Pelvic Floor Distress Inventory-20 (PFDI-20). Higher scores on the inventory indicated a greater severity of symptoms. To calculate the required sample size it was assumed that the watchful waiting group would have a PDFI-20 score of 60 points at baseline with no subsequent change in symptoms at three months. The sample size was based on having 80% power to detect a difference between treatment groups of 15 points (25% reduction) in the PFDI-20 score, with a standard deviation of 36 points at three month follow-up. To achieve this difference using a critical level of significance of 0.05 and two sided alternative hypothesis, 92 women were needed in each treatment arm. To account for an estimated dropout rate of 15%, the required sample size was adjusted to 216.

In total, 287 women were recruited and randomised to pelvic floor muscle training (n=145) or watchful waiting (n=142). Overall, 250 (87%) women completed follow-up. At the end of follow-up the intervention group had a significant improvement in symptoms compared with the watchful waiting group, with an average reduction of 9.1 (95% confidence interval 2.8 to 15.4; P=0.005) points on the PFDI-20.

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

  • a) The proposed difference between treatment groups of 15 points on the PFDI-20 used to …

View Full Text

Log in

Log in through your institution


* For online subscription