Open AccessAPPROACHES TO THE DESIGN OF DIAGNOSTIC ITEM MODELS
Author(s) -
Graf Edith Aurora
Publication year - 2008
Publication title -
ets research report series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.235
H-Index - 5
ISSN - 2330-8516
DOI - 10.1002/j.2333-8504.2008.tb02093.x
Subject(s) - item response theory , computer science , diagnostic test , scale (ratio) , item analysis , machine learning , diagnostic model , artificial intelligence , psychometrics , data mining , statistics , mathematics , medicine , emergency medicine , quantum mechanics , physics
Quantitative item models are item structures that may be expressed in terms of mathematical variables and constraints. An item model may be developed as a computer program from which large numbers of items are automatically generated. Item models can be used to produce large numbers of items for use in traditional, large‐scale assessments. But they have potential for use in other areas as well, including diagnostic assessment. In this report, I first review research on diagnostic assessment and then discuss how approaches to diagnostic assessment can inform the design of diagnostic item models.