Diagnostic tools can help schools more consistently and fairly match instructional resources to the needs of their students. To ensure the best educational outcome for each child, diagnostic decision-making systems seek to balance time, clarity, and accuracy. However, recent research notes that many educational decisions tend to be made using professional judgment alone. Judgments grounded on data, statistical models, and even informal prediction models, however, outperform those based on intuition alone. The purpose of this manuscript is to describe the theoretical basis for signal detection and methods for statistically evaluating diagnostic decisions in education. We make recommendations to help test developers and consumers apply this methodology to other diagnostic systems in education and interpret the use of signal detection methods for educational screeners and diagnostic tests.