Discriminant Validity Assessment Using AVE

The square root of the Average Variance Extracted (AVE) is a key metric used to assess the discriminant validity of a measurement model. Discriminant validity ensures that a construct is unique and distinct from other constructs.

Assessing Discriminant Validity

A common criterion for assessing discriminant validity is the Fornell-Larcker criterion. This method compares the square root of the AVE for each construct with the correlation between that construct and all other constructs in the model.

• If the square root of the AVE for a construct is greater than the absolute value of the correlation between that construct and any other construct, it provides evidence for discriminant validity.
• Mathematically, for a construct A and another construct B:

  $\sqrt{AVE_A} > |correlation(A, B)|$

This indicates that the shared variance between construct A and itself (as measured by AVE) is higher than its shared variance with any other construct, confirming it is distinct.

Distinguishing from Other Concepts

• Composite Reliability (e.g., Cronbach's Alpha, McDonald's Omega) measures the internal consistency of items within a single construct.
• Convergent Validity assesses the degree to which two measures of the same construct are correlated.
• Inter-rater Reliability measures the agreement between two or more independent raters.

The square root of AVE specifically addresses how well a construct differs from others, which is the definition of discriminant validity.