ABSTRACT
This chapter describes the methodology for making inferences with respect to the basic measures of test accuracy and begins with a section on the design of such studies. First, the elements of a good design for the accuracy of a medical test will be explained in the context of a protocol submission of a trial to assess the accuracy of a diagnostic test in a clinical situation. This will include describing in some detail the components of a clinical protocol, such as the objectives of the study, the background, patient and reader selection, the study plan, the number of patients, the statistical design and analysis, and finally the role that references (prior experimental studies) play in the protocol.
