Basic Validity

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…

Three-pronged classical construct-validity battery: (1) CONVERGENT — does the new scale correlate strongly (r ≥ 0.50) with established scales measuring the same construct?

(2) DISCRIMINANT — does it correlate weakly (r ≤ 0.30) with measures of unrelated constructs? (3) KNOWN-GROUPS — does it differentiate groups that should differ on the construct (clinical vs non-clinical, experts vs novices, etc.) via t / F? Reports per-criterion Pearson r + 95% CI, per-discriminant pair r + CI, and known-groups t/F + Cohen's d/η². The standard pre-CFA / alongside-CFA validity evidence.

Worked example

Does the scale relate to what it should — and not to what it shouldn't?

Convergent and discriminant validity were checked by correlating the scale with a related measure and an unrelated one.

Result

The scale correlated strongly with a related construct (r = .62) and weakly with an unrelated one (r = .11), supporting basic validity.

How you'd report it (APA)

The scale showed convergent (r = .62) and discriminant (r = .11) validity against reference measures.

When to use it

  • New scale — three-pronged validity validation
    New 15-item self-esteem scale validated alongside: Rosenberg Self-Esteem (convergent), Big Five Neuroticism (convergent), Locus of Control (discriminant), Numerical Reasoning (disc
  • Criterion validity — predictive against external marker
    Pre-employment cognitive ability test (n=300) correlated with 6-month job-performance ratings.

When NOT to — use instead

  • Internal-consistency reliability
    Basic validity is between-scale; for internal consistency use α / ω. → Cronbach's Alpha
  • Multi-construct CFA-based validity
    AVE / CR / HTMT are the modern SEM-based validity battery; use those when CFA is fitted. → AVE + CR + HTMT
  • Cross-cultural / cross-language validity
    Use cross_cultural for cross-cultural validity assessment (DIF + invariance + source-target). → Cross-Cultural Validity
  • Content validity (expert ratings)
    Content validity (CVR / CVI / Aiken V) is judged by experts, not data. → Content Validity

Assumptions (and what to do if they fail)

Scale + criterion are continuous (Pearson r assumes interval scale)medium

Check: See the assumption diagnostics in the workspace.

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

Known-groups variable is categorical with ≥ 2 levelsmedium

Check: See the assumption diagnostics in the workspace.

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

Listwise exclusion of missing pairsmedium

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 Basic Validity on your own data?

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

Run this test →