In conventional discourse, true score almost always has the Platonic connotation of “in the eye of God” truth. That is, there is no acknowledgment of the possibility of error of any type. This notion of true score may have some philosophical value, but it has no scientific utility. All measurements (i.e., scores) in scientific disciplines are observed under certain conditions of measurement, with the implicit acknowledgment that such measurements can differ under other conditions. There are two broad classes of perspectives on true score: expected-value perspectives and model-trait perspectives. The expected-value perspectives include classical test theory (CTT) and generalizability (G) theory, both of which view true score as the expected value of observed scores over replications of a measurement procedure. The only model-trait perspective considered ...
Looks like you do not have access to this content.