User Guide: EFA Readiness Checker

Welcome to the EFA Readiness Checker. This tool assists postgraduate students in evaluating their data before proceeding to advanced modeling (like CFA or Regression), ensuring the underlying constructs are valid.

1. What is EFA?

Exploratory Factor Analysis (EFA) is used to find underlying structure in a large set of variables. If you asked 20 questions on a survey, EFA helps group them into 3 or 4 broader "Factors" or "Dimensions" (e.g., Motivation, Anxiety, Engagement).

2. Data Suitability Thresholds

Before grouping items, your data must pass two tests:

KMO (Kaiser-Meyer-Olkin): Measures sampling adequacy. Must be > 0.6. Values closer to 1.0 are better.
Bartlett's Test of Sphericity: Tests if your items are correlated enough to run EFA. Must be significant (p < .05).

3. Extracting the Tables in SPSS

In SPSS, go to Analyze > Dimension Reduction > Factor...
Move your questionnaire items into the Variables box.
Click Descriptives and check "KMO and Bartlett's test of sphericity".
Click Extraction. Typically, select "Principal Axis Factoring".
Click Rotation. Choose "Promax" or "Direct Oblimin" (since social science factors usually correlate).
Click Options. Check "Sorted by size" and "Suppress small coefficients" (set absolute value below .30).
Run the analysis and paste the output tables into this tool.

4. The Danger of Cross-Loadings

A "loading" is a number showing how strongly an item belongs to a factor. We want items to load highly (e.g., > 0.5) on only one factor.

Cross-loading: If Item 5 loads at .55 on Factor 1 AND .50 on Factor 2, it is confusing. It measures both things simultaneously. This AI tool will flag cross-loadings so you can safely delete the item and re-run your SPSS analysis for a cleaner model.