Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain
the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in
Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles
and JavaScript.
Statistical analysis is an essential part of clinical practice, since the very concept of evidence-based medicine hinges on sound interpretation of clinical data. Using the Scandinavian prostatectomy versus watchful waiting study as a practical example, Andrew Vickers presents two common errors: accepting the null hypothesis and misinterpreting the lower statistical power of overall versus cancer-specific survival, and warns of the dangers of forgetting these basic principles.