Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Wright Map Analysis× | Many-Facet Rasch Measurement× | |
|---|---|---|
| Domaine | Education | Education |
| Famille | Latent structure | Latent structure |
| Année d'origine≠ | 2005 | 1989 |
| Auteur d'origine≠ | Benjamin Wright (Rasch measurement); construct-mapping framing by Mark Wilson | John Michael Linacre |
| Type≠ | Graphical display aligning person abilities and item difficulties on one scale | Rasch model extension adding rater and other facets to person and item |
| Source fondatrice≠ | Wilson, M. (2005). Constructing Measures: An Item Response Modeling Approach. Lawrence Erlbaum Associates. ISBN: 9780805847857 | Linacre, J. M. (1989). Many-Facet Rasch Measurement. MESA Press. ISBN: 9780941938020 |
| Alias | Item-Person Map, Item Map, Construct Map (Rasch), Variable Map | MFRM, Many-Faceted Rasch Model, Facets Model, Linacre Facets Model |
| Apparentées | 4 | 4 |
| Résumé≠ | A Wright map (item-person map) is the signature graphical output of Rasch measurement: it places persons and items on the same vertical scale, with examinee abilities on one side and item difficulties on the other, both in logits. Because a person succeeds on an item with probability one-half when their ability equals the item's difficulty, this shared scaling lets analysts see at a glance how well a test is targeted to its examinees, what the items reveal about the construct's order, and where measurement is sparse. Named for Benjamin Wright and central to Mark Wilson's construct-mapping approach, it is a primary tool for interpreting and validating measures. | Many-facet Rasch measurement (MFRM) extends the basic Rasch model to assessments mediated by raters. Beyond examinee ability and item difficulty, it adds explicit parameters for rater severity and for any other facet of the rating situation — task, occasion, rating criterion — placing them all on one common logit scale. Developed by John Michael Linacre, MFRM lets analysts estimate and adjust for the fact that some raters are systematically harsh and others lenient, producing 'fair' ability estimates that do not penalize an examinee for happening to draw a severe judge. |
| ScholarGateJeu de données ↗ |
|
|