Statistical efficiency in study design

Researchers are often faced with deciding which outcome measure to use for addressing the statistical hypothesis of a study. In this chapter, we address the question of statistical efficiency in study planning when choosing between viable endpoints and illustrate with two common biomedical examples that analysis of a binary endpoint is less efficient than working with the underlying continuous quantity that defines it. Efficiency is used here in the sense of evaluating sample sizes requirements to achieve the scientific goals of the research.