METHODS TO ESTABLISH VALIDITY AND RELIABILITY
by Albert Barber
1. Content Validity Evidence- established by inspecting a test question to see whether they correspond to what the user decides should be covered by the test.
1.1. Makes and measures objectives
2. Criterion-Related Validity Evidence- measures the legitimacy of a new test with that of an old test. Less expensive, shorter and can be administered to groups.
2.1. Makes sure a new test is reliable
2.1.1. Two Types of Criterion- Related Validity Evidence 1.Concurrent- deals with measures that can be administered at the same time as the measure to be validated. 2.Predictive- measures the subjects on whatever the test is suspose to predict after a period of time has elapsed.
3. Test - Retest or Stability- test is given twice and the correlation between the first set of scores and the second set is determined
3.1. Can determine if and how much data a student memorizes on a test.
4. Construct Validity Evidence- tells whether the results from a test correspond to what you would expect (based on your own knowledge about what is being measured) tells something about the construct validity for a test.
4.1. Predicts subsequent performance, success or failure in the next grade.
5. Alternate Forms or Equivalence- administers two forms of a equivalent test to a group of students, and the correlation b/w the two sets of scores is determined.
5.1. Eliminates the problems of memorizing material on the test.
5.1.1. Two Types of Internal Consistency 1.Split-half methods (odd-even)- items are divided in half and assigned to students 2.Kuder- Richardson methods- measures the extent to which items within one form of the test have as much in common with one another as do the items in that one form with corresponding items in an equivalent form.