Northern Illinois University

Office of Research, Evaluation and Policy Studies

Validity of Test Scores

Validity is an important characteristic of an instrument. It refers to the ability to measure, in a test, what was intended so that users can interpret the outcomes.

There are five types of evidence to demonstrate validity of test scores:

  1. Construct validity
  2. Content validity
  3. Predictive validity
  4. Concurrent validity
  5. Consequential validity

Threats to Internal Validity: Controlling extraneous variables will help the research to attribute the observed outcomes to the intervention. Factors affecting internal validity are:

  1. History
  2. Maturation
  3. Testing
  4. Instrumentation
  5. Statistical regression
  6. Differential selection
  7. Experimental mortality
  8. Selection-maturation interaction
  9. Compensatory rivalry by the control group
  10. Compensatory equalization of treatments
  11. Resentful demoralization of the control group

Threats to External Validity: This refers to the extent outcomes from a study can be applied to other individuals and settings. Factors affecting external validity are:

  1. Population validity
  2. Ecological validity

References:

Gay, L. R., and Airasian, P. (1997). Educational research. New Jersey, Ohio: Merrill.