Path: Janda's Home Page > Scale Construction > Outline
Measurement Validity

 

  • Validity: Do the indicators correspond to the concepts they are supposed to measure?
  • Scholars have elaborated different "forms" of validity and proposals for testing:
    • face validity
      • --easiest test to pass: does the method seem valid on its face?
      • --e.g., are pastors' recommendations a valid measure of academic potential?
    • content validity
      • --do the items cover the range of the attribute being measured?
      • --e.g., an academic potential test should include reading, writing, mathematics, and reasoning
    • criterion validity
      • --an academic potential test should predict to academic performance
      • --must have an external measure (criterion) of academic performance
    • construct validity--infers validity from theoretical relationships, e.g., academic potential
      • --academic potential might be expected to relate to such external variables as
        • record of reliability in employment
        • lack of a police record
      • --academic potential might be expected to relate to such internal variables as
        • ability to work independently
        • ability to withstand criticism
    • discriminant validity--the scale should be distinguishable from other concepts*
      • --academic potential should differ for students from the same school
      • --academic potential should differ from potential for business

    *For the classic paper on discriminant validity, see Donald T. Campbell and Donald W. Fiske, "Convergent and Discriminant Validation by the Multitrait-Multimethod Matrix," Psychological Bulletin, 56 (March, 1959), 81-105. This is one of the most frequently cited articles in the social science literature.