Hi
For PLS-SEM, my final results have composite reliability above 0.70 and AVE of most constructs above 0.40. For Discriminant validity, I have only used Fornell and Larcker criteria. Do you think these results are good enough?
@Omera For convergence of observed to latent factors, threshold for AVE is .50 or above. In your case, AVE values are above .40 but not .50 which refers to low convergence of observed items to their respective latent variables.
Imran Anwar Thanks for your reply. I cant delete more items from my study to achieve AVE above 0.50.
I have found these two references to support AVE less than 0.40.
We can accept AVE < 0.5 if the composite reliability is > 0.6, because the convergent validity of the construct is still adequate (Fornell & Larcker, 1981)
Fornell, C., & Larcker, D. F. (1981). Evaluating structural equation models with unobservable variables and measurement error. Journal of Marketing Research, 18, 39-50.
Hair, J., Black, W., Babin, B., and Anderson, R. (2010). Multivariate data analysis (7th ed.): Prentice-Hall, Inc. Upper Saddle River, NJ, USA.
Do you think these references are enough to justify my approach?
In discriminant validity , You should include not only Fornell larcker criterion but also HTMT and cross loadings alog with figures is more reliable.While your Composite reliability 0.70 and AVE is above 0.40 is fine don't worry
An AVE of less than 0.50 indicates that, on average, more error remains in the items than the variance explained by the construct.
- Badges
- Science topic
- Similar topics
- Instrumentation Engineering
- Instruments