ATI releases a research brief summarizing current research on Categorical Growth Analysis, a statistical method involving the repeated-measure t-test written by Sarah Callahan, Ph.D., Research Scientist with ATI.
As part of the growing implementation of instructional effectiveness initiatives, districts and schools have expressed a need for information about the growth of students for which each teacher and principal is responsible. To be useful, student growth must be estimated based on valid, reliable student assessments and categorized via robust statistical approaches. Via the Galileo® K-12 Online Instructional Improvement and Instructional Effectiveness System (IIIES), ATI provides districts/schools with a wide variety of valid, reliable assessments including instructional effectiveness (IE) pretests and posttests as well as integrated statistical approaches designed to provide districts/schools with precise information about student growth.
This research brief describes and illustrates the underlying method for one of the statistical approaches developed by ATI to provide information about student growth, Categorical Growth Analysis. Categorical Growth Analysis enables educators to evaluate growth throughout the year. Information about student growth can be accessed along with information about student achievement in Galileo reports and used to guide professional development, student intervention, and other activities. Categorical Growth Analysis supports a fair, constructive approach to educator evaluation that evaluates educators against a defensible standard while providing every educator with the opportunity to succeed. This brief also summarizes the results of a simulation study evaluating the appropriateness of the method underlying Categorical Growth Analysis for a wide range of possible datasets.
Read the full Research Brief.