NotesFAQContact Us
Collection
Advanced
Search Tips
ERIC Number: ED318786
Record Type: Non-Journal
Publication Date: 1990-Apr
Pages: 15
Abstractor: N/A
Reference Count: N/A
ISBN: N/A
ISSN: N/A
IRT as a Way of Improving the Usefulness of Complex Data.
Beaton, Albert E.; Johnson, Eugene G.
When the Educational Testing Service became the administrator of the National Assessment of Educational Progress (NAEP) in 1983, it introduced scales based on item response theory (IRT) as a way of presenting results of the assessment to the general public. Some properties of the scales and their uses are discussed. Initial attempts at presenting the assessment results reported the percent correct statistics for each individual item. IRT-based NAEP scales avoid the problems of average percent correct statistics and summarize complex information by reducing a large data set into a few manageable and interpretable summary statistics. The dimensionality of data sets has been studied to protect against losing important information in the summarization process. Research into scaling has demonstrated that, in most cases, the data support creating a single developmental scale. The NAEP also produces a global summary, using a weighted average of the domain scores. Scale anchoring is accomplished by describing what students at selected levels know and can do. A typical anchoring process is described. Three figures illustrate the use of NAEP scales. (SLD)
Publication Type: Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Identifiers - Assessments and Surveys: National Assessment of Educational Progress