Question- Discriminant validity-PLEASE help!

Frequently asked questions about PLS path modeling.
Post Reply
MaFa
PLS Junior User
Posts: 5
Joined: Fri Aug 23, 2019 11:32 pm
Real name and title: Ana Foster, PhD student

Question- Discriminant validity-PLEASE help!

Post by MaFa » Wed Sep 04, 2019 4:37 pm

Hello,
In my model, I have two independent variables, one moderator and one DV. The Fornell larcker test is ok, AVE is higher than correlations; however, I have high correlations between one IV and DV and also two DVs and one IV and moderator (higher than 0.7), also the items load on each other (higher than 0.6); but they load more on their own construct; can I justify that if there is only 0.1 difference?
Checking the HTMT shows that there are issues: the two IVs is 0.96 and the moderator and one IV is 0.95.
I am very confused! Is there any way to work on this model? The results of this model are very interesting and are paths can be justified well.
I really want to work on this model and finish the paper. Please let me know if you know any way I can fix the issue! My sample is 600.

Thanks a lot!

User avatar
cringle
SmartPLS Developer
Posts: 810
Joined: Tue Sep 20, 2005 9:13 am
Real name and title: Prof. Dr. Christian M. Ringle
Location: Hamburg (Germany)
Contact:

Re: Question- Discriminant validity-PLEASE help!

Post by cringle » Tue Sep 10, 2019 9:02 am

Can you merge the problematic constructs?

At the end of this article, you find some recommendations (flow chart): http://link.springer.com/article/10.100 ... 014-0403-8

Post Reply