HTMT discriminant validity

Frequently asked questions about PLS path modeling.
PLS Junior User
Posts: 6
Joined: Sun Jan 13, 2019 12:49 pm
Real name and title: Mr Steven Gregory Bamba

Re: HTMT discriminant validity

Post by StevenGregory » Mon Jan 14, 2019 6:31 am

ohh okey so Sir is it alright if i only using the cross loading test for the discriminant validity test?
because my cross loading test values are ok/valid as required
Thank you in advance Sir

SmartPLS Developer
Posts: 971
Joined: Tue Mar 28, 2006 11:09 am
Real name and title: Dr. Jan-Michael Becker

Re: HTMT discriminant validity

Post by jmbecker » Fri Jan 18, 2019 8:59 am

No it is not ok. See also my response here: viewtopic.php?f=5&t=1479.
If one of your tests shows discriminant validity problems you should address them and not just find another test that does not show problems (especially if that test is only a weak test of the problem).
You should try to fix your data and model problems. That would likely also resolve the HTMT value problems. Without fixing the problems the results from your analysis are not reliable and findings cannot be trusted.
Dr. Jan-Michael Becker, University of Cologne, SmartPLS Developer
Researchgate: ... v=hdr_xprf
GoogleScholar: ... AAAJ&hl=de

PLS Junior User
Posts: 1
Joined: Tue Mar 26, 2019 4:03 pm
Real name and title: Leon Bongers

Re: HTMT discriminant validity

Post by lebo01 » Tue Mar 26, 2019 4:37 pm

Dear Professor Ringle,

I have the same problem. The HTMT value for two constructs was found to be 0.945. As you suggested in another comment I bootstrapped HTMT (2-sided test with 10%). The values for the upper and lower bound are 0.897 and 0.991 (which indicates discriminant validity?), but I do not understand why I have to use a 10% probability of error with the 2-sided test instead of 5%. Do I only need to change it for bootstrapping HTMT or also for path coefficients etc.?
Thank you very much.

Kind regards

Post Reply