Skip to content

Glossary · Evaluation

Wilson interval

The Wilson score interval is a confidence interval for a proportion, such as a pass rate, that stays within 0–100% and keeps close to its stated coverage even for small samples and rates near 0 or 100%.

Also called Wilson score interval · Reviewed 15 November 2026

Proposed by E. B. Wilson in 1927, it is recommended over the textbook normal (Wald) interval by Brown, Cai and DasGupta, whose study showed the Wald interval's coverage can be badly off even at large n.

Kojen reports a 95% Wilson interval on every pass rate it measures.

Formula

(p̂ + z²/2n ± z·√(p̂(1−p̂)/n + z²/4n²)) / (1 + z²/n)

Learn more on Kojen

Sources

  1. [1]Wilson, E. B. (1927), JASA. Probable inference, the law of succession, and statistical inference
  2. [2]Brown, Cai & DasGupta (2001), Statistical Science. Interval Estimation for a Binomial Proportion

All 31 terms

Put the definitions to work.

Kojen evaluates, tunes and red-teams your agents with these methods built in: Wilson intervals, pass^k, LLM judges with visible components. Free to start.

Start training free