ABSTRACT
Many examinations are used to make a simple pass-fail decision. These have historically been called criterion-referenced tests, mastery tests, and other names. In this chapter, I generically refer to these types of examinations as mastery tests. At a somewhat abstract level, mastery testing is fairly straightforward. A test form is constructed to assess one or more knowledge and skill domains by some prescribed item selection process. A score scale is established for the test form and a standard is set denoting the passing score on the scale. Test takers who exceed the cut score are assumed to have met the established threshold of skills and knowledge-that is, they are “competent.” In addition to ignoring many important standard-setting issues, as well as glossing over a multitude of technical psychometric considerations, this abstracted view of mastery testing overlooks many important and sometimes complex issues specifically related to test design, item banking, and test assembly.
