When developing educational and psychological tests, particularly for high-stakes uses, psychometricians look carefully at the statistical properties of the items making up the test. In general, the goal is to calibrate statistically two key item indices—the items’ difficulty and their ability to discriminate among and between examinees. With respect to the latter characteristic, measurement specialists look at how well the test items discriminate among and between examinees with varying levels of the abilities measured by the test. Consider, for example, a test designed to select students for admission to college. This test ought to include items that discriminate between high- and low-achieving examinees—offering sound evidence in support of the colleges’ selection decisions.