ERIC Number: ED445077
Record Type: RIE
Publication Date: 2000-Jan-27
What Is Reliability Generalization, and Why Is It Important?
Cousin, Sherri L.; Henson, Robin K.
Researchers consistently fail to report reliability estimates for data used in their studies. This lack of reporting hinders appropriate evaluation and interpretation of data and may lead to inappropriate conclusions. Because reliability is inured to scores obtained from a test, and not the test itself, it is important to report score reliability in both measurement and substantive studies. Failure to report reliability estimates is a practice that plagues social science research and may undermine results across studies. Reliability generalization (RG) is a meta-analytic method that looks at the reliability of scores from tests and helps to determine what is causing measurement error across studies. RG has the potential to help researchers use specific tests more accurately and to help identify specific sample characteristics and other factors that influence and affect score data. The purpose of this paper is to discuss the sample dependency of score reliability, emphasize the importance of measurement, even in substantive studies, and explain the premises and procedures of RG. (Contains 1 figure, 1 table, and 29 references.) (Author/SLD)
Publication Type: Reports - Descriptive; Speeches/Meeting Papers
Education Level: N/A
Authoring Institution: N/A
Note: Paper presented at the Annual Meeting of the Southwest Educational Research Association (Dallas, TX, January 27-29, 2000).