8

• Validity


  The degree to which a test measures what it is supposed to measure
• Facets of Validity


  • Construct Validity
  • Content Validity
  • Criterion Validity
• Why is Validity Important?

  Without validity, assessment results are useless and attempts to help the client could end up harming them
• Relationship between Reliability and Validity

  A measure can be reliable but not valid, or reliable and valid
• Reliability-Validity Metaphor


  High reliability-low validity: Darts clustered but far from target

  Low reliability-low validity: Darts scattered across board

  High reliability-high validity: Darts clustered near target center
• Face Validity


  The degree to which an assessment or test subjectively appears to measure the variable or construct it is supposed to measure
• Face validity does not necessarily mean a test is a valid measure of a construct, just that it appears to be</b>
• Construct


  An attribute, skill, or ability that is based on established theories and exists in the human brain
• Construct Validity


  The degree to which a test measures the construct it is supposed to measure
• Construct Validity


  • Established by looking at numerous studies using the test

  Includes convergent validity (agreement with other validated tests of the same construct) and discriminant validity (lack of correlation with tests of different constructs)
• Threats to construct validity include not having a solid definition of the construct and not conducting enough research studies
• Hamilton Psychiatric Rating Scale for Anxiety

  A previously validated test that measures anxiety
• Low correlation with the Hamilton Rating Scale for Anxiety and the BDI

  Establishes discriminant validity
• Discriminant validity


  The extent to which a test measures what it is supposed to and not some theoretically unrelated construct
• Threats to Construct Validity:
• Threats to Construct Validity

  • Not having a solid definition of the construct
  • Not conducting enough research studies to prove construct validity
  • Losing connection between the theoretical construct and how it is experienced in the real world
  • Having administration and scoring procedures that interfere with the outcomes of the test
  • The expectations of the experimenter can influence the outcomes of a study
• Content Validity


  How accurately an assessment or measurement tool taps into the various aspects of the specific construct in question
• Measuring Content Validity


  1. Rely on the knowledge of subject-matter experts

  2. Provide experts with the measurement tool

  3. Ask experts to provide feedback on how well each question measures the construct

  4. Analyze the expert feedback

  5. Make informed decisions about the effectiveness of each question
• Content Validity in a Clinical Setting

  • Psychiatrists evaluate each question in an assessment tool designed to measure depression severity
  • Provide ratings on how well the wording of each question taps into measuring depression symptoms
  • Use the expert feedback to alter or eliminate questions that don't measure depression well
• Content Validity in a Business Setting

  • Retailers survey customers about their buying experience
  • Questions focused on aspects of customer service have high content validity
  • Questions about product affordability have lower content validity as it is a separate construct
• Content validity, while somewhat subjective, is a critical component of developing a high quality assessment tool
• Predictive Validity


  How well a specific tool predicts future behavior
• Determining Predictive Validity


  1. Calculate the correlation coefficient between the assessment results and the subsequent targeted behavior

  2. The stronger the correlation, the higher the degree of predictive validity
• Predictive Validity Example


  • Employers use personality assessments to hire conscientious employees
  • The assessment must accurately measure conscientiousness to have predictive validity
  • Assess conscientiousness through questions about timeliness, honesty, organization
  • Evaluate if high scorers on the assessment demonstrate those behaviors in the workplace
• Concurrent Validity


  The extent to which the results of a particular test or measurement correspond to those of a previously established measurement for the same construct
• Concurrent Validity Example


  • Psychologist develops a new depression test (Rice Depression Scale)
  • Compares it to an established depression test (Beck Depression Inventory)
  • Finds high positive correlation between the two tests
  • Concludes the Rice Depression Scale has concurrent validity