WE‐B‐201‐01: Introduction: Not Everything You Read Is True

Abstract

Evidence is growing to suggest that many published clinical results cannot be replicated. At the same time, the number of published clinical papers is steadily increasing and most if not all base their conclusions on evidence provided by formal statistical tests. Medical physicists have a critical need to understand and be able to interpret the methods and results of these studies in order to judge their scientific quality and relevance. However many medical physicists have minimal or no training in the sort of practical statistical methods commonly found in the literature. They may therefore have an inadequate ability to detect statistical errors and limitations that are an unfortunately too frequent occurrence in clinical papers.In this session we will use published examples to demonstrate common statistical errors frequently encountered in peer‐reviewed literature, distinctive symptoms that can help detect these errors, and explanations for how they might have been corrected. In the process, we will explain some of the basic concepts of inferential statistics. Some specific case studies we will cover will include misunderstanding the meaning of p‐values and clinical significance, misinterpreting statistical power, not accounting for multiple‐hypothesis testing, ignoring missing data, and faulty survival analysis. Learning Objectives: Learn about the presence of statistical problems in published studies Identify common signs and symptoms of potential problems in various types of statistical tests Learn methods for correctly implementing statistical analyses of the type commonly found in clinical publications