Endgames Statistical Question

Randomised controlled trials: understanding effect sizes

BMJ 2015; 350 doi: https://doi.org/10.1136/bmj.h1690 (Published 27 March 2015) Cite this as: BMJ 2015;350:h1690
  1. Philip Sedgwick, reader in medical statistics and medical education1
  1. 1Institute for Medical and Biomedical Education, St George’s, University of London, London, UK
  1. p.sedgwick{at}sgul.ac.uk

Researchers assessed whether a multimodal group exercise intervention had physiological, functional, and emotional benefits for patients with cancer. A randomised controlled trial was performed. The intervention was supervised exercise comprising high intensity cardiovascular and resistance training, relaxation and body awareness training, and massage. The intervention was delivered for nine hours weekly for six weeks in addition to conventional care. The control treatment was conventional care alone. Participants were 269 patients with cancer undergoing adjuvant chemotherapy or treatment for advanced disease. The primary outcome was fatigue at six weeks as assessed using the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire (EORTC QLQ-C30); scores range from 0 to 100 and higher scores represent higher levels of fatigue. Secondary outcomes included measures of physical capacity, general wellbeing, physical activity, and quality of life.1

At six weeks of follow-up, the fatigue score was significantly lower in the intervention group than in the control group (adjusted difference 6.6 points, 95% confidence interval 0.9 to 12.3; P=0.02). The difference between treatment groups in outcome was adjusted for baseline fatigue score, disease, and demographic covariates. The observed reduction in fatigue after the intervention compared with the control had an effect size of 0.33. The researchers also reported that the intervention significantly improved vitality, aerobic capacity, muscular strength, emotional wellbeing, and physical and functional activity. No significant effect was seen for quality of life.

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

  • a) The effect size was calculated using the standard error of the mean difference between treatment groups in fatigue

  • b) The effect size was measured on the same scale as …

View Full Text

Sign in

Log in through your institution

Subscribe