AVE + CR + HTMT

Verified

Psychometrics (legacy hub)

Independently verified. Every statistic this test reports has been re-derived against an independent reference — never the library the pipeline itself calls — the rendered output was read back in a browser, and the result is locked with a committed regression suite.

Run this test straight away on a free built-in teaching dataset — no data of your own needed — or bring your own. Either opens the guided workspace: variable setup, assumption diagnostics, results with effect sizes and confidence intervals, figures, and APA-ready reporting.

Loading teaching datasets…

Or use your own dataset

Loading your datasets…

Post-CFA construct-validity battery for multi-construct instruments.

Three statistics per latent factor: (1) Average Variance Extracted (AVE) ≥ 0.50 demonstrates convergent validity (factor explains majority of indicator variance); (2) Composite Reliability (CR) ≥ 0.70 confirms internal consistency from the CFA solution; (3) Heterotrait-Monotrait ratio (HTMT) < 0.85 demonstrates discriminant validity (construct distinguishable from other constructs). The modern Hair / Henseler standard for SEM-based validity reporting; supersedes the classical Fornell-Larcker √AVE comparison.

Worked example

Does the scale show convergent and discriminant validity?

Average variance extracted (AVE), composite reliability (CR) and the HTMT ratio assess the constructs' convergent and discriminant validity.

Result

All constructs had CR > .80 and AVE > .50 (convergent validity); every HTMT ratio was < .85 (discriminant validity holds).

How you'd report it (APA)

Constructs showed convergent validity (CR > .80, AVE > .50) and discriminant validity (all HTMT < .85).

When to use it

  • Multi-construct CFA — convergent + discriminant validity
    Marketing model: 4 latent constructs (perceived quality, brand image, satisfaction, loyalty), 4 items each, n=380.
  • PLS-SEM measurement-model validity reporting
    PLS-SEM technology-acceptance model with 5 latent constructs (perceived usefulness, perceived ease of use, attitude, intention, actual use).

When NOT to — use instead

  • Single-construct scale (no constructs to compare for HTMT)
    HTMT requires ≥ 2 latent constructs. → McDonald's Omega
  • Pre-CFA / no fitted measurement model
    AVE / CR / HTMT are computed FROM CFA loadings. → Confirmatory FA
  • Single-item indicators
    Single-item indicators have AVE = 1 by construction (uninformative); validity assessment requires multi-indicator constructs. → Basic Validity
  • Continuous-variable correlational analysis (not SEM)
    AVE / CR / HTMT are SEM-specific. → Basic Validity

Assumptions (and what to do if they fail)

Items measured on a continuous / Likert scalemedium

Check: See the assumption diagnostics in the workspace.

If violated: The workspace flags this and suggests a robust or nonparametric alternative.

Measurement model is correctly specifiedmedium

Check: See the assumption diagnostics in the workspace.

If violated: The workspace flags this and suggests a robust or nonparametric alternative.

Residuals are uncorrelated across items (standard CFA assumption)medium

Check: See the assumption diagnostics in the workspace.

If violated: The workspace flags this and suggests a robust or nonparametric alternative.

Listwise exclusion of incomplete response setsmedium

Check: See the assumption diagnostics in the workspace.

If violated: The workspace flags this and suggests a robust or nonparametric alternative.

Ready to run a AVE + CR + HTMT on your own data?

Guided setup, automatic assumption checks, effect sizes, figures and an APA write-up.

Run this test →