An Adjustment in p-Values for Multiple Endpoint Testing

In preclinical and pilot studies where various measurements are taken in order to gain an idea of the effectiveness or toxicity of an agent, it is important to control the overall Type I error rate when doing hypothesis testing. A review of some of the adjustments presently available in the literature is provided. Two adjustments to control the false–positive rate are proposed when the vector of test statistics is multivariate normal or asymptotically so. An example is used to illustrate the different techniques.