TY - GEN
T1 - Modeling Student’s Response Time in an Attribute Balanced Cognitive Diagnostic Adaptive Testing
AU - Wu, Tong
AU - Guo, Shaoyang
AU - Chang, Hua Hua
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
PY - 2022
Y1 - 2022
N2 - Nowadays, more and more people are paying attention to processing data in different fields. Following the ease of computer implementation within the classroom and test environment, Cognitive Diagnostic Computerized Adaptive Testing (CD-CAT) is a new advanced form of assessment. It combines the advantages of the Cognitive Diagnostic Model (CDM) and CAT, which could better assess students’ learning acquirement. More and more universities are applying this technique to the university course assessment (Morphew et al, Phys Rev Phys Educ Res 14(2):020110, 2018). To improve the applicability, accompany modern processing data use wise, many researchers have started implementing Response Time (RT) into CD-CAT. Two methods implementing Response Time (RT) with fulfilling attribute-balancing constraints is proposed: Time Weighted Modified Maximum Global Discrimination Index and Time Weighted Modified Posteriori Weighted Kullback-Leibler Information. These methods are compared in simulation with time-weighted non-attribute balancing methods. The result shows the proposed methods provide researchers with precise measurement accuracy as well as improvement in test efficiency.
AB - Nowadays, more and more people are paying attention to processing data in different fields. Following the ease of computer implementation within the classroom and test environment, Cognitive Diagnostic Computerized Adaptive Testing (CD-CAT) is a new advanced form of assessment. It combines the advantages of the Cognitive Diagnostic Model (CDM) and CAT, which could better assess students’ learning acquirement. More and more universities are applying this technique to the university course assessment (Morphew et al, Phys Rev Phys Educ Res 14(2):020110, 2018). To improve the applicability, accompany modern processing data use wise, many researchers have started implementing Response Time (RT) into CD-CAT. Two methods implementing Response Time (RT) with fulfilling attribute-balancing constraints is proposed: Time Weighted Modified Maximum Global Discrimination Index and Time Weighted Modified Posteriori Weighted Kullback-Leibler Information. These methods are compared in simulation with time-weighted non-attribute balancing methods. The result shows the proposed methods provide researchers with precise measurement accuracy as well as improvement in test efficiency.
KW - Attribute-balancing
KW - CD-CAT
KW - Item exposure control
KW - Measurement efficiency
KW - Response time
UR - http://www.scopus.com/inward/record.url?scp=85135091274&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85135091274&partnerID=8YFLogxK
U2 - 10.1007/978-3-031-04572-1_23
DO - 10.1007/978-3-031-04572-1_23
M3 - Conference contribution
AN - SCOPUS:85135091274
SN - 9783031045714
T3 - Springer Proceedings in Mathematics and Statistics
SP - 299
EP - 312
BT - Quantitative Psychology - The 86th Annual Meeting of the Psychometric Society, 2021
A2 - Wiberg, Marie
A2 - Molenaar, Dylan
A2 - González, Jorge
A2 - Kim, Jee-Seon
A2 - Hwang, Heungsun
PB - Springer
T2 - 86th Annual Meeting of the Psychometric Society, 2021
Y2 - 19 July 2021 through 23 July 2021
ER -