NotesFAQContact Us
Search Tips
ERIC Number: ED509322
Record Type: Non-Journal
Publication Date: 2010
Pages: 33
Abstractor: As Provided
Reference Count: 43
Investigating Effect of Ignoring Hierarchical Data Structures on Accuracy of Vertical Scaling Using Mixed-Effects Rasch Model
Wang, Shudong; Jiao, Hong; Jin, Ying; Thum, Yeow Meng
Online Submission, Paper presented at the Annual Meeting of the National Council on Measurement in Education (NCME) (Denver, CO, Apr 30-May 5, 2010)
The vertical scales of large-scale achievement tests created by using item response theory (IRT) models are mostly based on cluster (or correlated) educational data in which students usually are clustered in certain groups or settings (classrooms or schools). While such application directly violated assumption of independent sample of person in IRT, the consequence of such violation is usually ignored in practice. The purpose of this study is to investigate the effect of ignoring hierarchical data structures on the accuracy of vertical scaling by using regular Rasch model and mixed-effect or multilevel Rasch Model. The following is appended: Three-Level Models (Raudenbush & Bryk, "Hierarchical Linear Models: Application and Data Analysis Methods, Second Edition," page 228). (Contains 9 figures and 10 tables.)
Publication Type: Reports - Research; Speeches/Meeting Papers
Education Level: Elementary Secondary Education
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A