liveBook · Manning

Specificity

As explained in Timeless Algorithms, The Foundational Ideas

Specificity is the probability that a test gives a negative result when the condition being tested for is absent.

Specificity is the probability of a negative test result when the condition is absent: P(negative | condition absent). Its complement is the false-positive rate. In a decision about whether to order another test, specificity helps determine how test results update beliefs and whether added information is worth its cost. section 7.1.4

Table 7.3 Probabilities of each second test result given the true disease state.
True condition
Second test positive
Second test negative
Disease present
0.95
0.05
Disease absent
0.10
0.90

The second test has specificity 0.90: when disease is absent, it gives a negative result with probability 0.90 and a false positive with probability 0.10. section 7.1.4

How Timeless Algorithms, The Foundational Ideas covers it

How deep it goes
Defines specificity, relates it to the false-positive rate, and uses a numerical value to update disease probabilities.
Examples
Uses a second disease test with specificity 0.90 and false-positive rate 0.10.
What you can do after
Evaluate how test accuracy affects updated disease probabilities and the value of testing before acting.
How it connects
Connects specificity to sensitivity, false-positive rates, posterior probabilities, and value-of-information analysis.

Also explained in

Compare how 8 books explain specificity →

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.