Unit 8 · Questionnaires and reliability
How to run an exploratory factor analysis in SPSS
Run an EFA in SPSS: KMO and Bartlett’s test, eigenvalues, scree plots, rotation and reading the rotated component matrix.
Quick answer: How do you run an exploratory factor analysis in SPSS?
- Click Analyze › Dimension Reduction › Factor.
- Move the items into Variables.
- Under Descriptives… tick KMO and Bartlett’s test; under Extraction… tick Scree plot; under Rotation… choose Varimax or Direct Oblimin.
- Click OK, then read KMO, eigenvalues and the rotated matrix.
Report it in APA style: KMO = .84 and Bartlett’s test was significant, χ²(45) = 812.36, p < .001. Two factors explained 61.7% of the variance.
What is factor analysis?
Exploratory factor analysis (EFA) looks at the correlations among many items and finds a smaller number of underlying factors that explain them. It’s used to discover or check the structure of a questionnaire.
When to use it
- Developing a new questionnaire.
- Checking whether items group into the subscales you expect.
- A common guide is at least 5–10 participants per item, and ideally 200 or more overall.
How it works
First check the data are suitable: KMO (above .60) and a significant Bartlett’s test. Then decide how many factors to keep, using eigenvalues above 1 (Kaiser’s rule), the elbow of the scree plot, and whether the solution makes sense. Rotation makes the solution easier to interpret: Varimax keeps factors uncorrelated, while oblique methods such as Direct Oblimin allow them to correlate. Loadings (often above .40) show which items belong to which factor.
Assumptions
- Scale (or many-point ordinal) items that are related to each other.
- An adequate sample size.
- No extreme multicollinearity between items.
Worked example
Ten items gave two factors, study stress and social support, explaining 61.7% of the variance (KMO = .84). One item cross-loaded on both and was reviewed.
Key terms
- Factor
- An underlying variable that explains correlations among items.
- Loading
- How strongly an item relates to a factor.
- Eigenvalue
- The amount of variance a factor explains.
- Cross-loading
- An item loading substantially on more than one factor.
Common mistakes
- Using EFA with very small samples.
- Relying on Kaiser’s rule alone.
- Using Varimax when the factors are clearly related.
How to do it in SPSS
The SPSS syntax
Prefer typing to clicking? Open File › New › Syntax, paste this in, select it and choose Run › Selection. Every dialog's Paste button writes the same kind of code.
FACTOR
/VARIABLES st1 st2 st3 st4 st5 ss1 ss2 ss3 ss4 ss5
/PRINT INITIAL KMO EXTRACTION ROTATION
/FORMAT SORT BLANK(.30)
/PLOT EIGEN
/CRITERIA MINEIGEN(1) ITERATE(25)
/EXTRACTION PC
/ROTATION VARIMAX.Practice data
Download the file used in this lesson and run it yourself in SPSS. Your results will closely match the screens above, though a few numbers may differ slightly.
- stress_support_items.savTen study stress and social support items (N = 250)
Now practise it interactively →
Reading is only half of it. Tap through the real SPSS menus, read the output and pick the right write-up in 7 quick questions, with instant feedback on every answer.
Practice for this lesson is part of Pro, with every unit, unlimited hearts and saved progress.