Learning Objectives

Learning Objectives

After completing your study of this chapter, you should be able to do the following:

  • Explain what validity is.
  • Discuss the five sources of validity evidence described in the Standards for Educational and Psychological Testing ( AERA, APA, NCME, 2014).
  • Describe the general nature of the traditional terms content validity, criterion-related validity, and construct validity, and explain how these terms are related to the terms used in the Standards.
  • Explain, at a general level, the appropriate use of various validation strategies.
  • Describe and execute the steps involved in ensuring that a test demonstrates evidence of validity based on its content.
  • Describe methods for generating validity evidence based on the content of a test.
  • Explain the nature and importance of face validity and why it does not provide evi­dence for interpreting test scores.

 

Chapter Summary

Because decisions are made using psychological tests, it is important that the inferences made from the scores on psychological tests be justified and that test users administer tests only for their intended purposes. The validity of a test helps us understand whether the conclusions we are going to draw from test scores are appropriate and defensible. Traditionally, testing experts have evaluated three primary measures of validity: content, criterion related, and construct. The latest revision of the Standards for Educational and Psychological Testing (AERA, APA, & NCME, 2014) no longer refers to these traditional types of validity; instead, it cites five sources of evidence that a test is valid. It is usually not appropriate, or even possible, to estimate the validity of a test using all of these validation procedures. The strategy chosen to provide evidence of validity depends on the nature and purpose of the psychological test.

There are two methods for determining content-based evidence of validity of a test. The first involves performing a series of systematic steps during test development to ensure that the test samples the construct being measured representatively. The second method involves reviewing test items after the test development and determining the extent to which experts agree that test items are essential.

Although different from other evidence of validity, face validity—the perception of the test taker that the test questions are appropriate—is sometimes important to consider, especially in applied settings.