Discriminant Validity using the Fornell Larcker & HTMT

Questions about the implementation and application of the PLS-SEM method, that are not related to the usage of the SmartPLS software.
Post Reply
shash
PLS Junior User
Posts: 5
Joined: Sat Nov 25, 2017 2:29 pm
Real name and title: Ms. Shasheela Devi

Discriminant Validity using the Fornell Larcker & HTMT

Post by shash »

Hi,

For my model, the CR and AVE has been established. However, for discriminant validity test using the Fornell Larcker criterion gives below results:

A B C D E F
A 0.781
B 0.485 0.757
C 0.692 0.53 0.738
D 0.656 0.454 0.792 0.714
E 0.546 0.63 0.609 0.493 0.716
F 0.662 0.56 0.67 0.567 0.542 0.749

C is my mediator. D is my dependent variable (2nd order construct). AVE square root for C and D is slightly lower than the correlation value in RED. How do I interpret this? Discriminant validity achieved or not?

For HTMT, ONLY two of the values are slightly above 0.85. Is this still ok? Can I report that discriminant validity is achieved? Can someone please advise me. I am totally new to SmartPLS and I am lost. Thanks.
User avatar
cringle
SmartPLS Developer
Posts: 818
Joined: Tue Sep 20, 2005 9:13 am
Real name and title: Prof. Dr. Christian M. Ringle
Location: Hamburg (Germany)
Contact:

Re: Discriminant Validity using the Fornell Larcker & HTMT

Post by cringle »

You may want to revert to HTMT: https://www.smartpls.com/documentation/ ... t-validity

The paper by Henseler, J., Ringle, C. M., & Sarstedt, M. (2015). A New Criterion for Assessing Discriminant Validity in Variance-based Structural Equation Modeling. Journal of the Academy of Marketing Science, 43(1), 115-135. https://link.springer.com/article/10.10 ... 014-0403-8

shows that it has advantages compared to other criteria.

Best
CR
Post Reply