chapter
14 Pages

Module 6. Estimating Reliability

In Module 5, we stated that in classical test theory, reliability is a ratio of true score variance relative to total test variance. The more that observed scores reflect true score variance rather than error variance, the more reliable the measure. The less that observed scores reflect true score variance, the more that observed scores reflect error variance, and the less reliable the measure. When estimating reliability, however, it is essential to recognize that the differing methods for computing reliability consider different sources of error.