A statistical approach to the theory of psychological testing in which an individual's measured score is assumed to be equal to the true score plus random measurement error. The measurement error is usually assumed to have a mean of zero and to be uncorrelated with the true score. Within this theoretical framework, the reliability of a test item is defined as the proportion of the total variance in scores that is due to variance in the true scores. Also called classical measurement theory. The principal alternative is item response theory.