Unit 9 · Same people, several times

How to run a Friedman test in SPSS

Run a Friedman test in SPSS for three or more related conditions, with Kendall’s W and Bonferroni-corrected follow-ups.

Free tutorialPro practiceAbout 5 minutes6 practice questions

Quick answer: How do you run a Friedman test in SPSS?

  1. Click Analyze › Nonparametric Tests › Legacy Dialogs › K Related Samples.
  2. Move the related variables into Test Variables.
  3. Keep Friedman ticked and click OK.

Report it in APA style: Ratings differed across the three adverts, χ²F(2) = 7.58, p = .023.

Last updated November 2026 · Not sure this is the right test? Try the Which statistical test? tool.

What is the Friedman test?

The Friedman test is the non-parametric alternative to the repeated-measures ANOVA. It compares three or more related conditions using ranks within each person.

When to use it

  • The same people rate or are measured in three or more conditions.
  • Ordinal data, or Scale data that break repeated-measures ANOVA assumptions.

How it works

For each person, their scores across the conditions are ranked (1st, 2nd, 3rd). If conditions don’t differ, each condition’s mean rank should be similar. The test statistic is a chi-square with df = conditions − 1. Kendall’s W = χ² ÷ (N × (k − 1)) is an effect size from 0 to 1. Follow up with Wilcoxon tests using a Bonferroni-corrected α.

Assumptions

  • Related measurements from the same people.
  • Ordinal or Scale outcome.

Worked example

Ratings differed across three adverts, χ²F(2) = 7.58, p = .023, W = .16. Advert B had the highest mean rank.

Key terms

Mean rank
Average within-person rank of a condition.
Kendall’s W
Coefficient of concordance; effect size for Friedman.

Common mistakes

  • Using Kruskal-Wallis for repeated measures.
  • Skipping the correction on follow-up tests.

How to do it in SPSS

Friedman test

The nonparametric version of repeated-measures ANOVA: three or more related conditions with ordinal or non-normal data.

Tests for Several Related Samples
Variables
Participant ID [id]
▶
Test Variables:1
Rating advert A [advert_A]
Rating advert B [advert_B]
Rating advert C [advert_C]
Exact…Statistics…2
Test Type:
✓Friedman3
Kendall's W
Cochran's Q
OKPasteResetCancelHelp
  1. 1
    Test VariablesOne column per condition. Each person rated all three adverts.
  2. 2
    Statistics…Tick Quartiles for the medians.
  3. 3
    FriedmanFound under Legacy Dialogs › K Related Samples. Tick Kendall’s W as well if you want an effect size.

Reading Friedman output

Mean ranks show which condition came out on top; the test says whether the differences are significant.

Output1 [Document1] – SPSS Statistics Viewer
FileEditViewDataTransformAnalyzeGraphsUtilitiesExtensionsWindowHelp
Output
Log
NPar Tests
Friedman Test
Ranks
Test Statistics
Ranks
Mean Rank
advert_A1.63
advert_B2.421
advert_C1.95
Test Statistics
N24
Chi-Square7.582
df2
Asymp. Sig..0233

Friedman Test · Medians: A = 4, B = 5, C = 4

  1. 1
    Mean RankAdvert B was ranked highest on average.
  2. 2
    Chi-SquareFriedman’s test statistic, reported as χ²F(2) = 7.58.
  3. 3
    Asymp. Sig..023 is below .05, so at least one advert was rated differently. Follow up with Wilcoxon tests and a Bonferroni correction.

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.

NPAR TESTS
  /FRIEDMAN=advert_A advert_B advert_C
  /KENDALL=advert_A advert_B advert_C
  /STATISTICS QUARTILES.

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.

  • adverts.savRatings of three adverts by the same people (N = 24)

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 6 quick questions, with instant feedback on every answer.

Practice for this lesson is part of Pro, with every unit, unlimited hearts and saved progress.

More in Same people, several times