Testing is ubiquitous in education. From placement in specialized classes to college admissions, standardized exams play a large role in a child’s educational career. The introduction of the federal No Child Left Behind (NCLB) legislation in 2001, which required states to test all students in grades 3-8 in reading and math, dramatically increased the prevalence and use of test scores for education policymaking.
Contrary to popular belief, all modern cognitive assessments—including the new Common Core tests—produce test scores based on sophisticated statistical models rather than the simple percent of items a student answers correctly. There are good reasons for this, as explained below. The downside is that what we see as consumers of test scores depends on decisions made by the designers of the tests about characteristics of those models and their implementation. These details are typically hidden in dense technical documentation, if publicly available at all.