Analyses

Friedman test

Compare three or more repeated measurements by their ranks.

Edit on GitHub

When to use it

Use Friedman instead of a repeated-measures ANOVA when the same people are measured three or more times and the scores are ordinal or skewed.

Assumptions

Each row is one person. You need at least three measure columns. Kendall’s W is a separate analysis, not a field on this request.

Running it in Tensr

Analyze → Nonparametric Tests → K Related Samples. In chat: “Friedman test of t1, t2, and t3.”
Select at least three measure columns.

Options

Prop

Type

Reading the output

The three weekly scores. The later weeks tend to rank higher, without a person-by-person lockstep.

MeasureMean
week119.906
week220.889
week323.953

Significant differences across repeated measures (χ² = 9.556, p = .008, W = 0.133). Post-hoc pairwise comparisons recommended. Effect size (small; W < 0.1 negligible, 0.1 ≤ W < 0.3 small, 0.3 ≤ W < 0.5 moderate, W ≥ 0.5 large). Cutoffs: Tomczak & Tomczak, 2014. The primary result is significant (p = .008). This is large enough, in this sample, to treat the comparison this page is about as a real association rather than noise. Metrics: χ² = 9.556; df = 2; p-value = .008; Kendall's W = 0.133.

Reporting (APA 7)

Significant differences across repeated measures (χ² = 9.556, p = .008, W = 0.133). Post-hoc pairwise comparisons recommended. Effect size (small; W < 0.1 negligible, 0.1 ≤ W < 0.3 small, 0.3 ≤ W < 0.5 moderate, W ≥ 0.5 large). Cutoffs: Tomczak & Tomczak, 2014. This result is significant (p = .008). The effect is moderate, so report its size with the p-value.

Coming from SPSS

Analyze → Nonparametric Tests → K Related Samples.