Validity and Reliability (1)

Validity and Reliability (1)

1. Validity: is the most important consideration in developing and evaluating instruments.

   • It was defined as a way an instrument was measured.
     • Researchers cannot use the same instrument with different people.
       • There are no direct ways of measurement.

2. Construct underrepresentation: assesment that is too narrow and fails to include important dimensions of the construct.

   • Construct irrelevant variance: when test scores are affected by variables that are extraneous to the construct.

3. Validation: gathering evidence to support a particular interpretation of test scores.

   • Evidence based on test content: involves the content of the test, it should represent a balanced sample of relevant knowledge.
     • Content relevant validity evidence: it is focused on achievement tests.
       • Face validity: connection with a test content.
   • Concurrent validity: relationship between scores and criterion scores obtained at the same time.
     • Predictive validity: relationship between scores and criterion scores available at a future time.
       • Choosing a criterion: 1. The procedure depends on the relevance. 2. it should be reliable. 3. It should be free from bias.