Issues in the Hierarchy of Study Design, Hypothesis Testing, and Presentation of Results

Summary: Although evidence-based orthopaedics is sometimes perceived as a strict adherence to information obtained from randomized trials, it more accurately involves informed and effective use of all types of clinical evidence. However, any study that compares 2 or more treatments (ie, comparative study: randomized trial, observational study with control group, case–control) can be subject to the following errors in hypothesis testing: 1) A true positive result (ie, the study correctly identifies a true difference between treatments); 2) a true negative result (ie, the study correctly identifies no difference between treatment); 3) a false negative result–type II (beta) error (ie, the study incorrectly concludes no difference between treatments when a difference really exists); and 4) a false positive result–type I (alpha) error (ie, the study incorrectly concludes a difference between treatments when no difference exists). Understanding the principles of research design can limit errors and improve the validity of a study's results.