NotesFAQContact Us
Collection
Advanced
Search Tips
ERIC Number: ED406443
Record Type: Non-Journal
Publication Date: 1997-Jan-25
Pages: 24
Abstractor: N/A
Reference Count: N/A
ISBN: N/A
ISSN: N/A
Basic Concepts in Classical Test Theory: Relating Variance Partitioning in Substantive Analyses to the Same Process in Measurement Analyses.
Dawson, Thomas E.
The basic processes in univariate statistics involve partitioning the sum of squares into two components: explained and within. This paper explains that the same partitioning occurs in measurement analyses, i.e., splitting the sum of squares into reliable and unreliable components. In addition, it is shown how the three types of error inherent in all statistical analyses (i.e., sampling error, model specification error, and measurement error) impact any analysis the researcher attempts. Also emphasized is that tests are not reliable, but rather, that scores have varying degrees of reliability. The classical methods of estimating reliability are explained, with an emphasis on coefficient alpha. (Contains 6 figures, 6 tables, and 12 references.) (Author/SLD)
Publication Type: Reports - Descriptive; Speeches/Meeting Papers
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A