Step 1 · Data Input
Provide the correlation matrix (or raw ordinal data) and sample size.
Awaiting input
Quick Start
ℹ️
CSV / Excel: row 1 = variable names · next rows = correlation matrix.
Study Variables
Correlation Matrix
💡
Lower triangle or full matrix. One row per line.
Advanced: Ordinal data & Polychoric correlations
Export current matrix
Confirmatory Factor Analysis (CFA)
Tests whether your data fit a pre-specified factor model.
📘 How to specify a CFA model
How to specify: click + Add Factor, tick its items, repeat, then click ▶ Run CFA.
Fit indices — what's a good model?
CFI ≥ .95 · TLI ≥ .95 · RMSEA ≤ .05 (≤ .08 ok) · SRMR ≤ .08 · χ²/df < 3.
Structural Equation Modeling (SEM)
SEM extends CFA to test causal relationships between latent factors.
Direct vs indirect vs total effects
Direct = X→Y. Indirect = X→M→Y (= a × b). Total = Direct + Indirect.
Mediation Analysis (Bootstrap)
Calculate direct and indirect effects via Bootstrap
Import / Export Data
ℹ
CSV / Excel: Row 1 = variable names (X, M, Y), following rows = raw participant data.
Data Input (CSV or Paste)
💡Enter raw data (rows = participants, columns = X, M, Y). First row = headers.
Measurement Invariance Testing
Multi-group CFA — does your measurement model work across different populations?
📏 Levels of invariance
Configural → Metric → Scalar → Strict. Each accepted if ΔCFI ≥ -.010 (Cheung & Rensvold, 2002).
Group 1 (Current Data)
ℹ️ Group 1 uses the data loaded in Data Input. Run CFA first to confirm the factor structure.
Group 2 Data
ℹ️ Must have same variables and factor structure as Group 1. Expected variables: —
Validity & Reliability
Convergent validity, discriminant validity, and reliability assessment.
Acceptance criteria
Loadings ≥ .50 · AVE ≥ .50 · CR ≥ .70 · HTMT < .85 · √AVE > inter-factor r.
Full Results Summary
Comprehensive display of all results
⚠️Run CFA first to display results.