School psychologists often need to measure change in behavior or cognition across time and treatment conditions. This is typically done without consideration of issues such as reliability and statistical significance. This article presents a psychometrically sound model for determining when statistically significant change has occurred. Two theoretical datasets were created to represent scores obtained during baseline and follow-up, after theoretical interventions were emplaced. A Reliable Change Index (RCI; Jacobson and Truax, 1991) was calculated for each measure. Results indicate that some of the scores met the criteria for change, as defined by the RCI and the chosen confidence interval, while other scores did not meet the criteria. This illustrates that while a clinical review of a child’s performance might suggest substantive change, when the data are examined in a statistical framework, there may be inadequate evidence of statistically significant change; the difference between pre- and post-intervention scores might simply reflect measurement error.