A 5-day course in the theory and application of item response theory. As a prerequisite, participants should be proficient in the material covered in a one-semester graduate-level psychometrics course or an equivalent level of knowledge from professional experience in test development.
- Foundations, principles, and evolution of IRT
- The relationship between measurement, classical test theory, IRT, and factor analysis
- Linking terms and concepts in IRT, factor analysis, and classical test theory
- Assumptions of IRT models and their evaluation – test dimensionality and local independence
- The principle and implications of IRT model invariance
- Types of IRT models – model selection relative to test/instrument development and utility
- Unidimensional and multidimensional IRT
- Estimation of item parameters and person’s ability or latent traits
- Item and test information – definition, application, and implications for test development
- IRT-based test and instrument construction, evaluation, and refinement
- Steps in conducting an IRT analysis in relation to the testing problem
- Interpreting IRT output to inform test refinement
- Identification of potentially biased items and tests – techniques and practical solutions
- Introduction to longitudinal IRT
- Software used for conducting IRT analyses for a variety of models
Item response theory (IRT), also known as modern test theory, is a system of modeling procedures that uses latent characteristics of persons or examinees and test items as predictors of observed responses (de Ayala, 2022; Price, 2016; Lord, 1980). IRT is a model-based theory of statistical estimation that conveniently places persons and items on the same metric based on the probability of response outcomes. IRT offers a powerful statistical framework that is useful for experts in disciplines such as cognitive psychology, education, psychiatry, or social/developmental psychology when the goal is to construct explanatory models of behavior and/or performance in relation to theory. Participants will receive an electronic copy of all course materials, including lecture slides, practice datasets, software scripts, relevant supporting documentation, and recommended readings. Participants will also have access to a video recording of the course.
Instructor: Larry Price, Ph.D.
Larry Price, Ph.d. is a Professor of Psychometrics & Statistics and Director of the Office of Data Analytics & Methodology at Texas State University. Between 1999 and 2002, Dr. Price was employed at The Psychological Corporation in San Antonio as a Senior … Psychometrician/Statistician where his work focused on improving the psychometric properties of the Wechsler Scales of Intelligence Memory (e.g., WISC-III, WISC-IV, WAIS-III, WMS-III, and WPPSI-III), and Achievement (WIAT-II) and other psychological measures such as the Beck Depression Inventory (BDI) and Clinical Evaluation of Language Fundamentals (CELF-IV). His research interest includes the theoretical development and testing of Bayesian and non-Bayesian psychometric models in psychological and neuropsychological research (neuroimaging network analysis), theoretical development, testing, and refinement of classical and modern psychometric methods in the behavioral sciences, development of dynamic multivariate time series models for the psychological, social and neurosciences. Prior to working at Psychological Corporation, he worked at Emory University from 1986 to 1999 as a Biostatistician and Psychometrician in the School of Medicine. Funding mechanisms for Dr. Price’s work include NIH, NSF, DOE, and private organizations.
APA Continuing Education Credits:
This course offers 18hrs of credit hours for continuing education. Stats Camp Foundation is approved by the American Psychological Association to sponsor continuing education for psychologists. Stats Camp Foundation maintains responsibility for this program and its content.
Materials, downloads, recorded course video viewable for up to one year.