ABSTRACT
Generalizability (G) theory is a statistical theory for evaluating the dependability of behavioral measurements. G theory recognizes that an assessment might be adapted for particular decisions and so distinguishes a generalizability (G) study from a decision (D) study. An observed measurement can be decomposed into a component or effect for the universe score and one or more error components with data collected in a G study. G theory recognizes that the decision-maker might want to make two types of decisions based on a behavioral measurement: relative and absolute. G theory is essentially a random-effects theory. Typically a random facet is created by randomly sampling levels of a facet. Negative estimates of variance components can arise because of sampling error or model misspecification. Sometimes facets are 'hidden' in a G study and are not accounted for in interpreting variance components. A number of popular computer packages and programs provide estimates of variance components in generalizability studies.
