NotesFAQContact Us
Search Tips
ERIC Number: ED522412
Record Type: Non-Journal
Publication Date: 2011-Apr
Pages: 31
Abstractor: As Provided
Reference Count: 31
Effect of Person Cluster on Accuracy of Ability Estimation of Computerized Adaptive Testing in K-12 Education Assessment
Wang, Shudong; Jiao, Hong; He, Wei
Online Submission, Paper presented at the Annual Meeting of the American Educational Research Association (New Orleans, LA, Apr 8-12, 2011)
The ability estimation procedure is one of the most important components in a computerized adaptive testing (CAT) system. Currently, all CATs that provide K-12 student scores are based on the item response theory (IRT) model(s); while such application directly violates the assumption of independent sample of a person in IRT models because ability estimation is mostly based on cluster (or correlated) educational data in which students usually are clustered in certain groups or settings (classrooms or schools). The consequences of such violations are commonly ignored. The purpose of this study is to investigate the effect of ignoring hierarchical data structures of students sample on the accuracy of ability estimation by using a regular Rasch model. Results show that ICCs have not only statistically significant effect on the accuracy of a person's ability estimation, but also large effect sizes. (Contains 13 tables and 7 figures.)
Publication Type: Reports - Research; Speeches/Meeting Papers
Education Level: Elementary Secondary Education
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A