CFA (Confirmatory Factor Analysis)

Description

Tests whether survey items measure a pre-specified set of latent constructs as theorised, giving fit indices, loadings and evidence of construct validity.

Confirmatory factor analysis specifies in advance which items load on which latent factors (e.g. five trust items on Interface Trust, four on Institutional Trust) and tests how well this structure reproduces the observed covariance matrix. Unlike EFA, items are not allowed to load freely on all factors. CFA provides standardised loadings, factor correlations and global fit, and it is the measurement model underlying any SEM. Rigour comes from theory-led specification, adequate sample size (commonly 200 or more), appropriate estimators for ordinal Likert data (WLSMV), reporting multiple fit indices, examining convergent and discriminant validity, and testing measurement invariance before comparing groups.

Attributes

Loss type
Siloed
Stage
Evaluation
Effort
Weeks

Steps

  1. Specify the measurement model from theory or a prior EFA on a separate sample: which items load on which factors.
  2. Collect data from at least 200 respondents (more for complex models) and inspect item distributions.
  3. Fit the model with an estimator suited to the data (WLSMV for ordinal items, MLR for continuous-like items).
  4. Evaluate fit with CFI and TLI at or above 0.95, RMSEA at or below 0.06, and SRMR at or below 0.08.
  5. Check standardised loadings (ideally above 0.5, preferably 0.7), average variance extracted above 0.5 and discriminant validity (HTMT below 0.85).
  6. Test measurement invariance (configural, metric, scalar) before comparing groups, and avoid purely data-driven modification indices.

Sources

  • Principles and Practice of Structural Equation Modeling (Rex Kline)
  • A Primer on Partial Least Squares Structural Equation Modeling (Joseph Hair et al.)
  • DAGs+SEM Playbook (Vivek Gopinath)
  • Discovering Statistics Using R/SPSS (Andy Field)
  • Quantitative User Experience Research (Chris Chapman & Kerry Rodden)
  • Movie Booking Playbook (Vivek Gopinath)
  • Confirmatory Factor Analysis for Applied Research (Timothy Brown)
  • Principles & Practice of SEM (Kline)
  • Primer on PLS-SEM (Hair et al.)
  • DAGs+SEM Playbook (Gopinath)
  • The Inquiry Series, Ch 49 — Structural Equation Modeling — From Quotes to Coefficients
  • Discovering Statistics (Field)
  • Quantitative UX Research (Chapman)
  • Movie Booking Playbook (Gopinath)
  • The Inquiry Series, Ch 50 — Factor Analysis — Discovering the Latent Structure of Experience
  • Factor and Discriminant Analysis (Sauro & Lewis, MeasuringU training)
  • Tenenbaum, G. & Eklund, R. (eds), Handbook of Sport Psychology, 3rd ed. (2007)

Also known as

  • Confirmatory factor analysis
  • Measurement model
  • CFA

Categories

  • Analytics & Behaviour
  • Survey & Psychometrics