November 13, 2023

A random item effects generalized partial credit model with a multiple imputation-based scoring procedure

Authors:
Sijia Huang, Seungwon Chung, and Li Cai
Random item effects item response theory (IRT) models have received much attention for more than a decade. However, more research is needed on random item effects IRT models for polytomous data. Additionally, to improve the utility of this new class of IRT models, the scoring issue must be addressed. We proposed a new random item effects generalized partial credit model (GPCM), which considers both random person and random item and category-specific effects. In addition, we introduced a multiple imputation (MI)-based scoring procedure that applies to various random item effects IRT models. To evaluate the proposed model and scoring procedure, we analyzed data from a Quality of Life (QoL) scale for the Chronically Mentally III and conducted a preliminary simulation study.
Huang, S., Chung, S. & Cai, L. A random item effects generalized partial credit model with a multiple imputation-based scoring procedure. Qual Life Res 33, 637–651 (2024). https://doi.org/10.1007/s11136-023-03551-6