ABSTRACT

The ultimate aim of government agencies that regulate the marketing of new drugs is to ensure that the drugs that are available for people to use are safe and effective. However, regardless of how the decision to grant marketing approval is made, there will always be some drugs that are approved that are not effective. A measure of the quality of the decision rule for granting marketing approval should therefore compare in some way the number of drugs that are approved and effective relative to those that are approved and are ineffective. One such measure is the ratio of true positives to false positives. In this chapter, we develop the ratio of true to false positives and the ratio of power to type 1 error as measures of the strength of evidence in the design and evaluation of clinical trials.