Validity and Reliabliity
by Cindy Gann
1. Yield numerical indices of validity
2. Criterion Related Validity Evidence
2.1. 1. Concurrent Validity Evidence
2.1.1. anchor to criterion test
2.1.2. Determined by correlating test scores with a criterion measure collected at the same time
2.2. 2. Predictive validity evidence is determined by correlating test scores with a criterion measure collected after a period of time
2.2.1. Prodicts success in college
3. Rank/ Same
4. Content Validity Evidence
4.1. Yield numerical indices of validity
4.2. criterion exists/ anchor for test
4.3. based on systematic comparison
5. Constuct Validity Evidence
5.1. no citerion no anchor for test
5.2. Theory oriented
5.3. no previous measurement developed
6. Interpreting validity evidence
6.1. Group variability affects the strength of the validity coefficient.
6.2. Validity coefficients should be considered in terms of the relevance and reliability of the criterion or standard
6.3. . The adequacy of validity evidence depends on both the strength of the validity coefficient and the purpose of the test.
7. yield stable scores over repeated administrations
8. Obtained by administering the same test twice to the same group of individuals, with a small time interval between testing, and correlating the scores
9. Alternate-form estimates of reliability are obtained by administering two alternate or equiva-lent forms of a test to the same group and correlating their scores.
10. . Internal consistency estimates of reliability
10.1. two general categories
10.1.1. split-half
10.1.2. odd–even estimates and item–total correlations, such as the Kuder–Richardson (KR) procedure
10.1.3. Split-half and odd–even estimates divide a test into halves and correlate the halves with one another