Discriminant Validity
Discriminant validity is the degree to which a construct is empirically distinct from other constructs it should not be identical to.
What it means
Two constructs have discriminant validity when their measures do not overlap too much, meaning each one captures something the other does not. Without it, you cannot tell whether you are measuring one idea or two.
How it is tested
The preferred test is the HTMT ratio, which detects problems more reliably than the older Fornell-Larcker criterion (comparing the square root of AVE with inter-construct correlations) or cross-loadings (Henseler, Ringle & Sarstedt, 2015; https://doi.org/10.1007/s11747-014-0403-8).
How to report it
Report HTMT for each construct pair, with HTMT < .85 (or < .90 for similar constructs) as supporting evidence. The Fornell-Larcker table is often reported too. See the HTMT method page for the full procedure.
Frequently asked questions
How do I show discriminant validity?
Report HTMT below .85 (or .90 for similar constructs) for every construct pair, which is the most reliable evidence. Many authors also include a Fornell-Larcker table for completeness.
What if HTMT is too high?
A high HTMT suggests two constructs overlap. Reconsider whether they are truly distinct, remove items that load on both, or merge the constructs if they measure the same thing.
How to cite this page
If this page helped your research, you can cite it (APA 7):
Szymkowiak, A. (2026). Discriminant Validity. Explonia. https://explonia.com/glossary/discriminant-validity/
Last updated: July 2026
Run your whole study in one place
Build it, collect it, and get publication-grade analysis with a draft APA paragraph you can edit. Free to start. No credit card.
Start free