The use of a global statistical approach for the design and data analysis of clinical trials with multiple primary outcomes

Determining whether one treatment is preferred over others is a major goal of many clinical studies but can be complicated by the situation when no single outcome is sufficient to make the judgment. We present a useful global statistical test technique and the corresponding global treatment effect (GTE) measure for assessing treatment's global preference when multiple outcomes are evaluated together. Applications of these techniques in clinical trial design and data analysis are illustrated.