NotesFAQContact Us
Search Tips
ERIC Number: ED500497
Record Type: Non-Journal
Publication Date: 2008-Feb-6
Pages: 22
Abstractor: Author
Reliability Generalization (RG) Analysis: The Test Is Not Reliable
Warne, Russell
Online Submission, Paper presented at the Annual Meeting of the Southwest Educational Research Association (31st, New Orleans, LA, Feb 6-9, 2008)
Literature shows that most researchers are unaware of some of the characteristics of reliability. This paper clarifies some misconceptions by describing the procedures, benefits, and limitations of reliability generalization while using it to illustrate the nature of score reliability. Reliability generalization (RG) is a meta-analytic method developed "to characterize the mean measurement error variance across studies [using a particular instrument] and also the sources of variability of these variances across studies" (Vacha-Haase, 1998, p. 6). Like all meta-analyses, RG uses studies, rather than individuals, as the unit of analysis to help researchers find which study characteristics to predict or explain variability in observed score reliability coefficients.
Publication Type: Information Analyses; Reports - Evaluative; Speeches/Meeting Papers
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Grant or Contract Numbers: N/A