Practical and Methodological Considerations Regarding Reliability
Reliability refers to the level of consistency or stability in the values of the scores that an instrument elicits. Reliability has different manifestations and methods of evaluation. It is possible to speak of split-half reliability, test—retest reliability, or alternate-forms reliability. Although these types of reliability require different methods of measurement, they are all ways of indexing the amount of variance in a test that is the result of error in measurement. Thus, reliability measurement is an attempt to estimate the percentage of error variance (Anastasi, 1982).
KeywordsItem Response Theory Internal Consistency Reliability Latent Trait True Score Memory Item
Unable to display preview. Download preview PDF.