手法を比較

	ルール空間方法論	認知診断型コンピュータ適応型テスト	DINAモデル
分野	心理測定学	心理測定学	心理測定学
系統	Latent structure	Latent structure	Latent structure
提唱年	1983	2007	2001
提唱者	Kikumi K. Tatsuoka	Xueli Xu, Jean-Paul Fox	Brian Junker, Klaas Sijtsma
種類	IRT-based diagnostic classification	Skill-adaptive testing with psychometric diagnostic classification	Discrete latent class model
原典	Hartz, S. M. (2002). A Bayesian framework for the unified treatment of assessing dimensionality, assessing local dependence, and estimating ability for unidimensional and multidimensional item response data. Unpublished doctoral dissertation, University of Illinois at Urbana-Champaign.	Choi, K. M., Lee, Y. S., & Park, Y. S. (2015). What CDM can tell about examinees' strengths and weaknesses: Cognitive diagnostic information in TIMSS. Journal of Educational Evaluation for Policy Analysis, 24(1), 79-100.	Junker, B. W., & Sijtsma, K. (2001). Cognitive assessment models with few assumptions, and connections with nonparametric item response theory. Applied Psychological Measurement, 25(3), 258-272.
別名	RSM	CD-CAT	DINA
関連	5	5	4
概要	Rule Space Methodology (RSM) is a diagnostic classification approach developed by Tatsuoka (1983) that uses Item Response Theory and geometric methods to classify examinees into knowledge states based on their response patterns. Unlike classical scoring, RSM identifies which specific skills or competencies an examinee possesses or lacks, enabling targeted educational interventions.	Cognitive Diagnostic Computerized Adaptive Testing (CD-CAT) combines computerized adaptive testing (CAT) with cognitive diagnostic models (CDMs) to efficiently assess students' specific skill profiles. Rather than producing a single overall ability score, CD-CAT adaptively selects items to quickly identify which skills a student has mastered and which need development.	The DINA Model (Deterministic Inputs, Noisy Outputs) is a cognitive diagnostic model developed by Junker and Sijtsma (2001) that classifies examinees into latent skill classes based on their item response patterns. DINA assumes a deterministic relationship between skill mastery and correct responses, with probabilistic error accounting for guessing and slips.