Analyses

Fleiss’ kappa

Agreement among three or more raters.

Edit on GitHub

When to use it

Use Fleiss’ kappa when three or more raters each code the same cases. Cohen’s kappa is the two-rater version.

Assumptions

Each column is one rater. Every rater uses the same categories. Tensr needs at least three rater columns.

Running it in Tensr

Analyze → Scale → Fleiss Kappa. In chat: “Fleiss’ kappa for these rater columns.”
Select at least three columns. Categories are inferred from the values unless you pass a list.

Options

Prop

Type

Reading the output

Three raters on the same 80 essays. Agreement beyond chance should be moderate, not perfect.

CategoryProportion
10.279
20.417
30.304

Fleiss' κ for 3 raters across 80 subjects. The primary result is significant (p = < .001). This is large enough, in this sample, to treat the comparison this page is about as a real association rather than noise. Metrics: κ = 0.447; SE = 0.065; z = 6.93; p-value = < .001; 95% CI = [0.321, 0.574].

Reporting (APA 7)

Fleiss' κ for 3 raters across 80 subjects. This result is significant (p = < .001). The effect is moderate, so report its size with the p-value.

Coming from SPSS

Analyze → Scale → Fleiss Kappa.