Discriminant Validity Analysis
Updated 2026-08-10
INTRODUCTION
English translation pending.
CORE DEFINITION
A step in construct validity testing that checks whether a measure of one construct can be distinguished from measures of related constructs. If two constructs correlate as strongly as their reliabilities allow, the evidence suggests they are the same construct or that the items are confounded. The key qualification is that discriminant validity complements convergent validity: demonstrating that a scale measures something is insufficient without also showing it does not measure something else. Common criteria include the Fornell-Larcker comparison and the HTMT ratio.
SCAFFOLDING EFFECT
Reduce cognitive load
- Comparison design: collect data on the target construct and on constructs it might be confused with. - Criterion check: apply a stated threshold such as the AVE square root or the HTMT ratio. - Item review: revisit items and construct boundaries when the criterion is not met.
Anchor fast decisions
Self-report items written for different constructs overlap in wording, so a scale can appear valid while measuring a neighboring concept. Comparing the shared variance within a construct against the variance it shares with others exposes that overlap. When the two are close, the items cannot separate the constructs, which means any conclusion drawn from the measure inherits the ambiguity.
MINIMUM ACTION
In progress 0/1Practice this model in one real situation:
account_treeGenealogyexpand_more
menu_bookReferencesexpand_more
Source support: Explicit
- en.wikipedia.orghttps://en.wikipedia.org/wiki/Discriminant_validityverified
PRIVATE NOTES · Only visible to you
SAVED Q&A
ENTRY Q&A · Private saving available
Ask with a clear boundary
thinkingmodels answers from published entry context only.
Your question is sent to thinkingmodels. The answer uses public entry context only.
RELATED MODELS