Method-Toolbox
Sample size estimation in Item Response Theory
Although Item Response Theory (IRT) models offer well-established psychometric advantages over traditional scoring methods, they have been largely confined to specific areas of psychology, such as educational assessment and personnel selection, while their broader potential remains underutilized in practice. One reason for this is the challenge of meeting the (presumed) larger sample size requirements, especially in complex measurement designs. Accurate a priori sample size estimation is essential for obtaining accurate estimates of item/person parameters, effects, and model fit. As such, it serves as an essential tool for effective study planning, especially in pre-registration and registered reports.
In the project “Potential Identification in Elementary School for Individual Support” (PINGUIN), we are developing a screening tool to objectively and reliably assess students’ cognitive potential and initial learning conditions at school entry. The computer-based assessment of the PINGUIN project consists of four modules: (1) cognitive potential, (2) language skills, (3) early literacy, and (4) basic mathematical competencies. For each module, tasks are selected adaptively from a comprehensive item bank. The study is conducted in small groups at school using tablets. PINGUIN is designed to help identify children’s potential at an early stage, to provide an objective and fair evaluation of their initial learning conditions, and provide individual support. Teachers can use the knowledge of each child’s individual strengths and weaknesses to tailor their teaching.