Cohen’s Kappa Calculator
Inter-rater agreement for two raters and two categories from a 2×2 table — observed agreement, expected agreement, κ and its interpretation.
How it works
κ = (pₒ − pₑ) ÷ (1 − pₑ)
Raw percent agreement is inflated by chance — two raters flipping coins agree half the time. Kappa subtracts the agreement expected from each rater’s marginal frequencies and rescales so that 1 is perfect agreement and 0 is chance level.
Worked example
a=20, b=5, c=10, d=15 (n=50): pₒ = 0.70, pₑ = (25×30 + 25×20)/2500 = 0.50, κ = 0.40 — fair-to-moderate.
Frequently asked questions
More than two categories or raters?
Use weighted kappa for ordered categories and Fleiss’ kappa for three or more raters. This tool handles the common 2×2 case.
Why can kappa be low when agreement is high?
When one category dominates, chance agreement is already high, so kappa has little room to grow — the “kappa paradox”.
Related calculators
For education — check assumptions (sample size, distribution) before using statistics in real decisions.