Construct Validity

Criterion Validity
1. evaluates how closely your measure's results align with those from existing, valid measures
  1. Concurrent Validity
    1. distinguishing participants appropriately
      1. e.g. if assessing a new measure of depression, participants should be separated into two groups: depressives and non-depressives
  2. Predictive Validity
    1. measure's ability to predict future outcomes
      1. e.g. reading scores at 7yo's predictive power of academic performance at 17
Content Validity
1. all aspects of the construct are being assessed
  1. e.g. if construct pertains to personality, does the measure assess the 5 main traits? (OCEAN)
Face Validity
1. the measure's content seems suitable
  1. e.g. does a test with math questions appear to be a relevant measure of arithmetic ability?
Discriminant (Divergent) Validity
1. shows two measures that are not supposed to be related are in fact, unrelated
  1. correlation coefficient can be used to prove dissociation
Convergent Validity
1. two similar measures of the construct are significantly correlated (r= >.5, ideally >.7)
  1. e.g. studying exam anxiety (construct) via a survey and participant observation. Convergence or correlation of scores shows both are measuring the same construct

Resource summary

	Created by Julia Swain about 3 years ago