Shavelson, R. J., & Webb, N. M. (1991).Generalizability Theory: A Primer. SAGE Publications, Incorporated.http://ebookcentral.proquest.com/lib/harvard-ebooks/detail.action?docID=6636862

Generalizability theory utilizes ANOVA to dissect the variability within social science measurements, similar to how researchers assess the impact of independent variables. This approach partitions a person's score into effects for the universe score, error sources (facets), and their combinations. The goal is to identify and quantify the impact of various error sources on measurements. A person's observed score is seen as a composite of the grand mean, person effect, item effect, and residual error, each having a corresponding variance component. Venn diagrams visually represent these variance components, illustrating how total variance is decomposed into constituent parts. This partitioning helps pinpoint major sources of measurement error and estimate total error magnitude.

keepSave to notecopy_alldocsAdd noteaudio_magic_eraserAudio OverviewschoolBriefing doc