ASSESSMENT OF FIT OF ITEM RESPONSE THEORY MODELS: FULLINFORMATION AND LIMITED-INFORMATION METHODS, ITEM AND
PERSON FIT ANALYSIS, AND BEYOND
Presented by SANDIP SINHARAY, (ETA) RESEARCH INSTITUTE
Friday, 10/11/2024, 11:15am ET, AUST 110
Virtual:
Meeting Link
Meeting # 2631 084 2277
Password: RMMESTAT
Item response theory (IRT) is one of the central methodological pillars supporting many
large and high-profile assessment programs globally. IRT analysis is essentially a type of
discrete multivariate analysis and is performed using IRT models that are latent variable
models for discrete data. However, IRT models involve multiple assumptions like
conditional independence, monotonicity etc. and the results obtained from IRT models may
not be accurate if one or more of the assumptions are not met, that is, if there is IRT model
misfit. This presentation will include a comprehensive review of the literature on the
assessment of fit of IRT models. The presenter will discuss various approaches and concepts
regarding IRT model fit including full-information and limited-information methods,
residual analysis, item and person-fit analysis, Bayesian methods, analysis for differential
item functioning, and assessment of practical significance of misfit. A real data example
will be used to illustrate some of the approaches. One goal of the presentation is to
stimulate discussions involving the audience members regarding IRT model-fit assessment.
Dr. Sandip Sinharayis a distinguished presidential appointee at the
Educational Testing Service (ETS) in Princeton, New Jersey. He is the current
editor of Psychometrika and a past editor of the Journal of Educational
Measurement and Journal of Educational and Behavioral Statistics. He has
received seven awards from the National Council on Measurement in
Education. These awards include the Outstanding Service Award, Bradley
Hanson Award, Annual Award for Outstanding Technical or Scientific
Contribution to the Field of Educational Measurement, and Jason Millman
Promising Measurement Scholar Award. Dr. Sinharay received the ETS
Scientist award in 2008 and the ETS Presidential award twice. He has coauthored a book on subscores, coedited two published volumes including the
Handbook of Statistics, Volume 26, on psychometrics (that he co-edited with
Prof. C. R. Rao), and authored or coauthored more than 150 articles in peerreviewed journals and edited books. His research, which has often been
funded by National Science Foundation and Institute of Education Sciences,
focuses on item response theory, assessment of model fit, reporting of
subscores, statistical methods for detecting test fraud, Bayesian methods, and
application of advanced statistical methods to education.