liveBook · Manning

Recall

As explained in Timeless Algorithms, The Foundational Ideas

The true positive rate is the proportion of actually positive cases correctly identified.

Recall, also called sensitivity or the true positive rate, is the probability that a test returns positive when the condition is present. It measures detection among actual positive cases—not the probability that a person has the condition after testing positive. section 2.2.2 section 10.2.1

P(D | H)=0.99

This conditional probability states the test’s sensitivity: D means the test is positive, and H means the disease is present. section 2.2.2

A positive test is not a diagnosis

With disease prevalence of 0.001, sensitivity of 0.99, and a 0.01 false-positive rate, a positive result gives an approximately 9% probability of disease. The test detects most cases, but the rare condition means positive results are not conclusive. section 2.2.2 section 10.2.1

How Timeless Algorithms, The Foundational Ideas covers it

How deep it goes
Defines sensitivity conditionally and relates missed cases to its complement, using the measure within Bayesian updates rather than developing it separately.
Examples
Uses medical tests with sensitivities of 0.99 and 0.95 to illustrate updating disease probabilities.
What you can do after
Evaluate how a positive test contributes to disease probability without mistaking sensitivity for the probability of disease after a positive result.
How it connects
Links sensitivity to Bayes’ theorem, specificity, false negative rate, false positive rate, and posterior probability.

Also explained in

Compare how 35 books explain recall →

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.