liveBook · Manning

Binomial test

As explained in Timeless Algorithms, The Foundational Ideas

A binomial test is an exact statistical test for assessing whether the observed number of successes in fixed independent binary trials is consistent with a specified success probability.

A binomial test assesses whether a count of successes in independent binary trials is consistent with a specified success probability. Under the null hypothesis, each trial is modeled with the same probability of success; an exact test calculates probabilities from the binomial distribution rather than a large-sample approximation. section 4.2.3

Small clinical trial

If 14 of 20 patients recover and the historical recovery probability is 50%, a one-tailed test asks how likely 14 or more recoveries would be under that baseline. The exact probability is approximately 0.057. section 4.2.3

How Timeless Algorithms, The Foundational Ideas covers it

How deep it goes
Calculates an exact tail probability and contrasts the method with large-sample approximations, without detailing the remaining decision steps.
Examples
Uses a 20-patient drug trial with 14 recoveries against a 50% historical baseline.
What you can do after
Evaluate how unusual an observed success count would be under a specified null probability.
How it connects
Connects hypothesis testing with null hypotheses and the chi-square test for categorical data.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Timeless Algorithms, The Foundational Ideas. The section links point to the parts of the book it draws on.