Reliability and Validity

1441 Words6 Pages
Running head: RELIABILITY AND VALIDITY Reliability and Validity Demetria M. Williams Research and Evaluation, PYCL-0507 (Summer 2013) Reliability and Validity Two concepts necessary for defining and measuring bias or distortion in an assessment are reliability and validity. There are four types of reliability used most frequently in assessments: Test-retest, alternate-forms, internal consistency, and interrater reliability. The three most frequently used validity procedures are content, criterion-related, and construct validity. The purpose of this paper is to define the types of reliability and validity, discuss how they are applied and their relevance to research. Reliability Reliability takes into account the extent to which an assessment is consistent. It answers the question, ‘How consistent and stable is a test when measuring the intended subject?’ The four types of reliability are test-retest, alternate forms, internal consistency, and interrater reliability. Test-Retest Reliability Test-retest reliability is when a single group of people (animal or thing) is tested twice with the same instrument of measure separated by a period of time. IQ tests and surveys are prime candidates for test-retest methodology, because there is very little chance of people experiencing a sudden increase in IQ or suddenly changing their opinions on a particular subject. It is expected that the shorter the time gap, the higher the correlation. Alternate Forms Reliabilty Unlike test-retest which evaluates over a period of time, alternate-forms reliability is when the indented population (people, animal, and/or thing) is measured with two forms of the same instrument. The American College Testing Program, an academic exam for college admissions, is an example of alternate-forms reliability testing. Within the

More about Reliability and Validity

Open Document