Comparer des méthodes

	Multilevel Item Response Theory	Modélisation multiniveau
Domaine	Education	Statistiques de recherche
Famille	Latent structure	Process / pipeline
Année d'origine	2010	1992
Auteur d'origine	Adams, Wilson & Wu; Fox & Glas; De Boeck & Wilson	Anthony Bryk and Stephen Raudenbush
Type	Item response models with a multilevel structure on the latent ability	Method
Source fondatrice	Fox, J.-P. (2010). Bayesian Item Response Modeling: Theory and Applications. Springer.	Bryk, A. S., & Raudenbush, S. W. (1992). Hierarchical Linear Models: Applications and Data Analysis Methods. SAGE Publications.
Alias	Multilevel IRT, MLIRT, Hierarchical IRT, Explanatory Item Response Models	HLM, mixed-effects models, random effects models, MLM
Apparentées	4	3
Résumé	Multilevel item response theory (MLIRT) joins two powerful frameworks: an IRT measurement model that turns item responses into a latent ability, and a multilevel structural model that explains how that ability varies across nested groups such as classrooms, schools, or countries. Instead of first scoring a test and then running a multilevel regression on the scores, MLIRT does both at once, so that measurement error in ability is properly carried into the group-level analysis. It is the rigorous way to study how student and school characteristics relate to a latent trait measured by a test.	Multilevel modeling (also called hierarchical linear modeling, mixed-effects modeling) is a statistical framework for analyzing data organized in nested or clustered structures—students within schools, patients within hospitals, repeated measures within individuals. Developed by Bryk and Raudenbush (1992), it accounts for dependency among observations and partitions variance into levels (within-cluster and between-cluster), enabling valid inference and revealing context effects. Essential in education, medicine, organizational research, and any field where data have natural hierarchies.