Overview

Specificity is the share of truly negative cases that a test correctly identifies as negative. High specificity means few false alarms.

Enter true positives, false negatives, true negatives and false positives from your test results. For a medical test, ask a clinician to interpret it.

Worked examples

InputsResult
True Positives88False Negatives12True Negatives190False Positives18Sensitivity: 88%Specificity: 91.35%PPV: 83.02%NPV: 94.06%
Show 2 more examples
True Positives45False Negatives5True Negatives900False Positives50Sensitivity: 90%Specificity: 94.74%PPV: 47.37%NPV: 99.45%
True Positives99False Negatives1True Negatives95False Positives5Sensitivity: 99%Specificity: 95%PPV: 95.19%NPV: 98.96%

Sensitivity by true positives

With the calculator's starting values, the sensitivity is 88%. The table shows how it changes with the true positives.

True PositivesSensitivity
6083.33%
8086.96%
88starting value88%
10089.29%
12090.91%

Other inputs: False Negatives: 12 · True Negatives: 190 · False Positives: 18. Change them in the calculator above for your own numbers.

How it works

Sensitivity is the share of real positives the test catches: TP ÷ (TP + FN). Specificity is the share of real negatives it correctly clears: TN ÷ (TN + FP). PPV and NPV show how often a positive or negative result is correct, and those depend on how common the condition is in the group tested.

The formula

Specificity = TN ÷ (TN + FP)
TP, FNReal positives caught and missed
TN, FPReal negatives cleared and false alarms

Practical tips

  • 190 true negatives and 18 false positives give a specificity of 91.35%.
  • A highly sensitive test is good for ruling a condition out, and a highly specific one for ruling it in.
  • False positive rate is 100% − specificity.

Frequently asked questions

Which matters more?

It depends on whether missing a case or raising a false alarm is worse.

Why do PPV and NPV change between groups?

They depend on prevalence. The same test gives a lower PPV where the condition is rarer.

Is specificity the same as precision?

No. Precision is PPV, the share of positive results that are correct.