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

Chapter 62

Planning a Group-Randomized Trial

David M. Murrary

62.1 Introduction

Planning a group-randomized trial (GRT) is a complex process. Readers interested in a more detailed discussion might wish to consult Murray’s text on the design and analysis of GRTs [1], from which much of this article was abstracted. Donner and Klar’s text is another good source of information [2].

62.2 The Research Question

The driving force behind any GRT must be the research question. The question will be based on the problem of interest and will identify the target population, the setting, the endpoints, and the intervention. In turn, those factors will shape the design and analytic plan.

Given the importance of the research question, the investigators must take care to articulate it clearly. Unfortunately, that does not always happen. Investigators may have ideas about the theoretical or conceptual basis for the intervention, and often even clearer ideas about the conceptual basis for the endpoints. They may even have ideas about intermediate processes. However, without very clear thinking about each of these issues, the investigators may find themselves at the end of the trial unable to answer the question of interest.

To put themselves in a position to articulate their research question clearly, the investigators should first document thoroughly the nature and extent of the underlying problem and the strategies and results of previous efforts to remedy that problem. A literature review and correspondence ...