liveBook · Manning

T-test

As explained in Timeless Algorithms, The Foundational Ideas

A t-test is a statistical test for comparing means using a t-distribution under specified assumptions.

A one-sample t-test compares a sample mean with a target when the population standard deviation is unknown and the population is assumed approximately normal. The sample mean’s departure from the target is scaled by estimated variability to produce a t-statistic. section 4.2.1

Test choice follows the research question, measurement type, and assumptions. A two-tailed test is appropriate when departures in either direction matter; the null sets the population mean equal to the target, while the alternative says it differs. section 4.2.1

Checking beverage fill volumes

A manufacturer tests whether average fill differs from 12 ounces. For a random sample of 20 containers, the mean is 11.85 ounces and the sample standard deviation is 0.30 ounces. The test evaluates that difference relative to estimated sampling variability. section 4.2.1

How Timeless Algorithms, The Foundational Ideas covers it

How deep it goes
Explains test selection and interprets the standardized statistic, without giving a numerical statistic or final decision.
Examples
Tests beverage-container fill volumes against a 12-ounce target using a sample of 20.
What it assumes
Assumes continuous measurements, an unknown population standard deviation, and an approximately normal population.
What you can do after
Evaluate a sample mean against a target by standardizing its difference using estimated sampling variability.
How it connects
Connects to null and alternative hypotheses, two-tailed testing, and Type I error.

Also explained in

Compare how 3 books explain t-test →

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.