Validity

1. in this form of checking for reliability, two test are made and the correlation between them is determined. If there is a large difference in the scores, the test is not going to be reliable.

2. Should a test be made up of questions that are similar, then the reliability can be measured using the split-halves method. Split-halves works by splitting the tests into two equal sections and finding the correlation between them. Because this can only be used if the similar items are scattered across the test, the implication is that this may not be very useful for assessing the reliability of tests.

3. The same test is given twice to see if they yield similar results. The implication of this to learning and assessment is that tests that yielded very low results both times need revision. Tests that yield high scores one day, and low then next are not showing reliability, and the teacher will have to determine if the problem was the test, or another factor.

4. A test has construct validity evidence if the evidence corresponds with a theory. This is important to learning and assessment because this will show teachers if enough time was spent on a unit before the test was taken. It may show areas which should have been reviewed prior to testing.

5. This is used to predict how well students will do in settings. such as classes, that they will have to take. This is important for educators who are trying to determine if a student needs to move from an average class to an honors course next year, or if they will need a remedial course instead of a tougher one.

6. Predictive Validity Evidence

7. Construct Validity Evidence

8. Importance to Learning & Assessment

8.1. The importance of validity and reliability is that they will help teachers determine if a test should be administered as is, changed, or done away with.

9. Reliability

9.1. Test-Retest or Stability

9.2. Alternative Form

9.3. Internal Consistency

10. Validity determines if a test is measuring what it is made to measure. Reliability determines if the test is able to consistently yield similar scores.

11. is done by measuring a new test against a more well-established test for the same objective. Both tests would be given to students and then the teacher would need to find the correlation between the two sets of scores. The importance of this to learning and assessment is that teachers can use new tests which may be less expensive, or more user-friendly to the students, and feel confident that the test is valid.

12. This determines if the test looks valid, but cannot determine if there is an issue with the construction of the test questions. It is used to go over the questions to see if they align with the objectives the teacher wants to assess. The importance for learning and assessment is that teachers are able to see if adjustments need to be made so that they are not testing for the wrong objectives.

13. Content Validity Evidence

14. Criterion-Related Validity Evidence

14.1. There are two types of Criterion-Related Validity Evidence, concurrent and predictive.

15. Concurrent Criterion-Related Validity Evidence