Methods and Applications of Statistics in Clinical Trials, Volume 1: Concepts, Principles, Trials, and Designs

Chapter 23

Control Groups

Stephanie Green

23.1 Introduction

A control group for a clinical trial is a group of uniformly treated patients selected to be compared with a group receiving a test (new or different) treatment. For the comparison to be a valid assessment of differences in outcome due to test treatment, the two groups must be as similar as possible with the exception of treatment. Various types of control groups are employed, and the choice is critical to the interpretation of a trial [1]. The type chosen for a particular trial will depend on many factors such as availability of resources, subjectivity of the primary outcome, availability of effective treatments, current extent of knowledge concerning treatment, severity of disease, and ethical considerations. Randomized trials comparing a control group with an experimental treatment group are the most convincing and reliable method for minimizing bias and demonstrating effectiveness of new treatments. Depending on standard of care, control groups for randomized trials may be patients randomized to no treatment, a placebo (i.e., an inactive agent or a procedure with the appearance of the new treatment), or standard active therapy with or without a placebo. Because of practical and ethical constraints, not all clinical questions can be addressed with a randomized trial. Nonrandomized controlled trials can have specific comparator groups or be controlled in the sense that carefully chosen historical information from the ...