NotesFAQContact Us
Collection
Advanced
Search Tips
Back to results
Peer reviewed Peer reviewed
ERIC Number: EJ314657
Record Type: Journal
Publication Date: 1985
Pages: N/A
Abstractor: N/A
ISBN: N/A
ISSN: N/A
EISSN: N/A
Available Date: N/A
The Regression Bias Method: A Unified Approach for Detecting Item Bias and Selection Bias.
Raju, Nambury S.; Normand, Jacques
Educational and Psychological Measurement, v45 n1 p37-54 Spr 1985
The Regression Model, popular in selection bias research, is proposed for use in item bias detection, providing a common framework for both types of bias. An empirical test of this new method, now called the Regression Bias method, and a comparison with other commonly used item bias detection methods are presented. (Author/BS)
Descriptors: Achievement Tests, Intermediate Grades, Item Analysis, Junior High Schools, Measurement Techniques, Regression (Statistics), Research Methodology, Selection, Test Bias, Test Items, Test Validity
Publication Type: Journal Articles; Reports - Research
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Identifiers - Assessments and Surveys: SRA Achievement Series
Grant or Contract Numbers: N/A
Author Affiliations: N/A