Seminar in Psychometrics

COMPS seminar main page

Nonparametric item response theory as an alternative to parametric item response theory

Date and time: Tuesday, May 9, 2023 (2:00 PM CET)
Place ICS CAS room 318, Pod Vodárenskou věží 2, Prague 8, also on Zoom.

Abstract. To analyze items and test a common approach is to use either sum scores or parametric item response theory (IRT). For binary scored items the common approach is to use the logistic one, two or three parameter IRT model and for polytomously scored items one typically uses the graded response model for likert scaled items or the generalized partial credit model when we can give partial credit on an item. In this talk, nonparametric item response theory methods, so called optimal scoring methods are discussed in light of their parametric counterparts. Comparisons are given which illustrate that nonparametric approaches sometimes are superior. Results based on both real data and simulated data will be presented and discussed.

Wiberg, M., Ramsay, J. O., & Li, J. (2019). Optimal scores: an alternative to parametric item response theory and sum scores. Psychometrika, 84(1), 310-322.
Ramsay, J., Li, J. & Wiberg, M. (2020). Better rating scale scores with information-based Psychometrics. Psych, 2(4), 347-369,
Ramsay, J.O, Li, J., & Wiberg, M. (2020). Full information optimal scoring. Journal of Educational and Behavioral Statistics, 45(3), 297-315.

Marie Wiberg
Umeå University, Sweden

Marie Wiberg is professor in Statistics with specialty psychometrics at the Department of Statistics, USBE, Umeå University, Sweden. Her research has focused on both parametric and nonparametric item response theory (IRT), test score equating as well as international large-scale assessments. She has developed new test score equating methods as well as nonparametric IRT methods.