Skip to main content

normalWaldBinomialInterval

Normal (Wald) interval p̂ ± z·SE, clamped to [0, 1].

normalWaldBinomialInterval(successes: number, nTrials: number, z: number): WilsonScoreInterval

Import​

const poker = require('poker-calculations');

ESM (Node):

import { createRequire } from 'module';
const require = createRequire(import.meta.url);
const poker = require('poker-calculations');

When to use​

Quick normal approximation bands when n is moderately large and the proportion is not extremely close to 0 or 1. Prefer wilsonScoreInterval or agrestiCoullInterval for small n or edge proportions.

How to use​

const poker = require('poker-calculations');

const successes = 250;
const nTrials = 500;
const z = 1.96;

const wald = poker.normalWaldBinomialInterval(successes, nTrials, z);
const wilson = poker.wilsonScoreInterval(successes, nTrials, z);

console.log({ wald, wilson, pHat: successes / nTrials });

Returns​

WilsonScoreInterval — { lower: number, upper: number } from p̂ ± z·√(p̂(1−p̂)/nTrials), with endpoints clamped to [0, 1].