Jämför metoder

	Multilevel Item Response Theory	Raschmodell
Ämnesområde	Education	Psykometri
Familj	Latent structure	Latent structure
Ursprungsår	2010	1960
Upphovsperson	Adams, Wilson & Wu; Fox & Glas; De Boeck & Wilson	Georg Rasch
Typ	Item response models with a multilevel structure on the latent ability	Item Response Theory / Latent trait model
Ursprungskälla	Fox, J.-P. (2010). Bayesian Item Response Modeling: Theory and Applications. Springer.	Rasch, G. (1960). Probabilistic Models for Some Intelligence and Attainment Tests. Danish Institute for Educational Research, Copenhagen.
Alias	Multilevel IRT, MLIRT, Hierarchical IRT, Explanatory Item Response Models	1PL IRT, one-parameter logistic model, Rasch Modeli — 1PL IRT, 1PL model
Närliggande	4	6
Sammanfattning	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.	The Rasch model, introduced by Georg Rasch in 1960, is the simplest member of the Item Response Theory (IRT) family. It assigns a single difficulty parameter to each test item and places both item difficulties and person abilities on the same logit scale, enabling direct, sample-independent comparison of items and persons.