Free tool that turns the results of a confirmatory factor analysis (CFA) into an APA 7 report: a standardized-loadings table with composite reliability (omega) and average variance extracted (AVE) per factor, a fit-index table graded against the Hu and Bentler (1999) cutoffs, a results paragraph in English or Spanish, and a path diagram (ellipses for latent variables, rectangles for indicators) downloadable as a high-resolution PNG with no watermark. It accepts the lavaan standardized solution pasted as text and fills in the grid for you.
Worked example: a 3-factor CFA of a 9-item self-efficacy scale (EAE-type, N = 482). Fit: χ²(24) = 48.10, p = .002, CFI = .97, TLI = .96, RMSEA = .049, 90% CI [.030, .068], SRMR = .041. Loadings ranged from .66 to .83; omega per factor .78, .79 and .80; AVE .54, .56 and .57; factor correlations from .47 to .58.
Which omega should I report after a CFA? The composite reliability computed from the loadings, omega = (Σλ)² / ((Σλ)² + Σ(1 − λ²)), equivalent to McDonald omega; unlike Cronbach alpha it does not assume equal loadings. What is an acceptable AVE? At least .50 (Fornell and Larcker, 1981), although with composite reliability ≥ .60 a somewhat lower AVE can still be defensible.
APA 7 loadings table with omega and AVE, fit traffic light (CFI, TLI, RMSEA, SRMR) and a high-resolution PNG path diagram, no watermark. Free for research.
| Index | Cutoff |
|---|---|
| χ² | Sensitive to sample size; always reported |
| χ²/df | ≤ 2 good; ≤ 3 acceptable |
| CFI | ≥ .95 good; ≥ .90 acceptable |
| TLI | ≥ .95 good; ≥ .90 acceptable |
| RMSEA [90% CI] | ≤ .06 good; ≤ .08 acceptable |
| SRMR | ≤ .08 good; ≤ .10 acceptable |
Cutoffs from Hu and Bentler (1999); χ²/df from Schermelleh-Engel et al. (2003). They are guidelines, not laws: interpret the whole set, not a single index. A significant χ² does not invalidate the model in a large sample, because the test picks up minimal discrepancies.
Composite reliability: ω = (Σλ)² / [(Σλ)² + Σ(1 − λ²)], equivalent to McDonald’s omega. Unlike Cronbach’s alpha it does not assume equal loadings.
Average variance extracted: AVE = Σλ² / k. At least .50 is expected (Fornell & Larcker, 1981), although with composite reliability ≥ .60 a somewhat lower AVE can be defensible.
Hu, L., & Bentler, P. M. (1999). Cutoff criteria for fit indexes in covariance structure analysis. Structural Equation Modeling, 6(1), 1–55. Schermelleh-Engel, K., Moosbrugger, H., & Müller, H. (2003). Evaluating the fit of structural equation models. Methods of Psychological Research Online, 8(2), 23–74. Fornell, C., & Larcker, D. F. (1981). Journal of Marketing Research, 18(1), 39–50.
If you use it in your thesis or in a paper, cite it so that readers of your Methods section know how the calculation was done.
Ciudad-Fernández, V. (2026). Confirmatory factor analysis APA report generator [Web application]. Ciudad Science. Retrieved October 14, 2026, from https://analisisdedatospsicologia.com/en/tools/cfa-apa-report-generator
For your Methods section: Confirmatory factor analysis fit was judged against the Hu and Bentler (1999) cutoffs and convergent validity with the AVE (Fornell & Larcker, 1981); the APA-style write-up of the results was prepared with the Ciudad Science confirmatory factor analysis APA report generator (Ciudad-Fernández, 2026).
@misc{ciudadfernandez2026reporteafc,
author = {Ciudad-Fern{\'a}ndez, V{\'i}ctor},
title = {{Confirmatory factor analysis APA report generator}},
year = {2026},
publisher = {Ciudad Science},
howpublished = {Web application},
url = {https://analisisdedatospsicologia.com/en/tools/cfa-apa-report-generator},
urldate = {2026-10-14},
note = {Accessed 2026-10-14},
}