🧮  Wilson Score Interval

Wilson Score Interval#

An accurate confidence interval for a proportion, robust for small samples.

Important

✨ AI-generated content. This page was written with the assistance of an AI language model and is provided as a learning aid. Despite careful review, it may still contain mistakes, omissions, or out-of-date information. Whether you are new to the topic, a team lead, or a senior practitioner, treat it as a starting point rather than an authoritative reference: read it critically and independently verify anything you act on (code, commands, figures, and factual claims) against official documentation and primary sources before relying on it.

What it is#

The Wilson score interval is a well-calibrated confidence interval for a binomial proportion, derived by improving the crude normal-approximation (Wald) interval. Introduced by E. B. Wilson in 1927, it is asymmetric and always stays within [0, 1].

Why it’s better#

Unlike the Wald interval, it doesn’t overshoot past 0 or 1 and doesn’t collapse to zero width when the observed proportion is 0 or 1; and unlike Clopper–Pearson, it isn’t overly conservative — its coverage sits close to nominal, so its intervals are narrower. That balance makes it the recommended default in most applications.

The caveats#

Its coverage can dip slightly below nominal for a few awkward proportions, and for extremely small samples the guaranteed Clopper–Pearson may still be safer. A continuity-corrected variant exists for tighter coverage.


Theme: Statistical Inference & Power  ·  All terminology



See also

Source article Adapted (context, re-expressed) in our own words from: Wilson Score Interval (insightful-data-lab.com).

Tags: purpose: reference topic: terminology level: beginner