【摘 要】
：
Multi-Stage Testing(MST) is a form of computerized testing which aims to overcome the disadvantages of CAT.It incorporates most of the advantages of CAT and linear testing.Cognitive Diagnosis Assessme
【机 构】
：
Jiangxi Normal University,China
论文部分内容阅读
Multi-Stage Testing(MST) is a form of computerized testing which aims to overcome the disadvantages of CAT.It incorporates most of the advantages of CAT and linear testing.Cognitive Diagnosis Assessment(CDA) aims to determine whether or not examinees have each of many attributes or skills underlying responses to test items.
其他文献
The past decade or so has been very productive related to adaptive models for test administration.It is clear that much of this work builds on the extensive application of CAT test designs and attenda
As with CAT,simulation techniques play critically important roles in MST development and evaluation.Because MST implementation and administration differs significantly from typical CAT,many existing C
Pearsons Research & Innovation Network was established in 2012 to produce rigorous,policy-relevant scholarship and invent capabilities and tools that support engaging,meaningful,and personalized learn
Item Response Theory(IRT) models can be used to evaluate the relationships between a latent trait of interest and the items intended to measure the trait.
Many methods have been developed for investigating Differential Item Functioning(DIF).Holland and Thayer developed an approach using Mantel-Haenszel statistics(Mantel & Haenszel.1959) in detecting DIF
Scenario Based Testing(SST) is designed to evaluate candidates on various situations that occur in a simulated workplace.
Psychopathology is characterized by disturbed emotion dynamics.This is currently a hot topic in psychological research.
The ceiling effect is a method effect that is observed in items that are too easy for almost all or even all members of the sample.Such an effect leads to skewness and impairs the suitability of maxim
A Thurstonian IRT model(Brown & Maydeu-Olivares,2011;2013) was developed to overcome the problems of ipsative data in multidimensional forced-choice questionnaires.
This study aims to evaluate the performance of Differential Item Functioning(DIF) detection methods(Mantel-Haenszel,Logistic Regression,Lords Chi Square and Rajus Signed Area) for Cognitive Diagnosis