Statistics: sensitivity, specificity, predictive values and likelihood ratio's
On this page
A = True Positive
B = False Positive
C = False Negative
D = True Negative
Sensitivity
Definition: The ability of a test to correctly identify those with the disease (true positives).
Formula:
Sensitivity = A / (A + C)
= True Positives / All with disease
Formula:
Specificity = D / (B + D)
= True Negatives / All without disease
Formula:
PPV = A / (A + B)
= True Positives / All positive test results
Formula:
NPV = D / (C + D)
= True Negatives / All negative test results
LR+ = Sensitivity / (1 − Specificity)
Negative Likelihood Ratio (LR−)
LR− = (1 − Sensitivity) / Specificity
B = False Positive
C = False Negative
D = True Negative
| Condition Positive | Condition Negative | |
|---|---|---|
| Test Outcome Positive | A | B |
| Test Outcome Negative | C | D |
Sensitivity
Definition: The ability of a test to correctly identify those with the disease (true positives).
Formula:
Sensitivity = A / (A + C)
= True Positives / All with disease
Specificity
Definition: The ability of a test to correctly identify those without the disease (true negatives).Formula:
Specificity = D / (B + D)
= True Negatives / All without disease
Positive Predictive Value (PPV)
Definition: The probability that a person with a positive test result actually has the disease.Formula:
PPV = A / (A + B)
= True Positives / All positive test results
Negative Predictive Value (NPV)
Definition: The probability that a person with a negative test result truly does not have the disease.Formula:
NPV = D / (C + D)
= True Negatives / All negative test results
Likelihood Ratios
Positive Likelihood Ratio (LR+)LR+ = Sensitivity / (1 − Specificity)
Negative Likelihood Ratio (LR−)
LR− = (1 − Sensitivity) / Specificity