手法を比較

	Standardized Test Analysis	項目応答理論 (IRT)
分野	Education	心理測定学
系統	Latent structure	Latent structure
提唱年	2014	1952–1968
提唱者	Educational measurement profession (AERA/APA/NCME Standards; Lord; Cronbach)	Frederic M. Lord (and Allan Birnbaum for the 2PL/3PL models)
種類	Psychometric evaluation of items, reliability, validity, and fairness of standardized tests	Probabilistic measurement model
原典	American Educational Research Association, American Psychological Association, & National Council on Measurement in Education. (2014). Standards for Educational and Psychological Testing. AERA. ISBN: 9780935302356	Lord, F. M. & Novick, M. R. (1968). Statistical Theories of Mental Test Scores. Addison-Wesley.
別名	Standardized Testing Analysis, Test Score Analysis, Item and Test Analysis, Educational Test Psychometrics	IRT, latent trait theory, item characteristic curve theory, modern test theory
関連	3	5
概要	Standardized test analysis is the body of psychometric methods used to evaluate and score standardized educational tests: analyzing how items perform, estimating reliability and the standard error of measurement, scaling scores via classical or item response theory, and assembling validity and fairness evidence. Governed by the professional Standards for Educational and Psychological Testing and rooted in test theory synthesized by Lord and others, it is the disciplined work that turns a set of test questions into defensible scores carrying meaning, precision, and fairness.	Item response theory models the probability that a respondent answers an item correctly (or endorses it) as a function of the respondent's latent trait level and the item's own statistical properties — difficulty, discrimination, and guessing. Unlike classical test theory, IRT places persons and items on the same scale, yielding measurement that is sample-independent for items and test-independent for persons.