Negative Predictive Value Calculator

Calculate the Negative Predictive Value (NPV) of a diagnostic test by entering your true positives, false negatives, false positives, and true negatives from a 2×2 contingency table. You can also supply a custom disease prevalence (%) when your sample doesn't reflect the real population. Results include NPV, PPV, sensitivity, specificity, and both likelihood ratios — giving you a full picture of test performance.

Number of cases where the disease is present AND the test result is positive.

Number of cases where the disease is present BUT the test result is negative.

Number of cases where the disease is absent BUT the test result is positive.

Number of cases where the disease is absent AND the test result is negative.

%

If your sample sizes don't reflect real-world prevalence, enter the true population prevalence here. Leave blank to use the prevalence derived from your table.

Results

Negative Predictive Value (NPV)

--

Positive Predictive Value (PPV)

--

Sensitivity

--

Specificity

--

Positive Likelihood Ratio (LR+)

--

Negative Likelihood Ratio (LR−)

--

Disease Prevalence Used

--

Test Result Breakdown

Frequently Asked Questions

What is Negative Predictive Value (NPV)?

NPV is the probability that a person who tests negative truly does not have the disease. It is calculated as True Negatives ÷ (True Negatives + False Negatives). A high NPV means a negative result is very reliable for ruling out disease.

How does disease prevalence affect NPV?

NPV rises as disease prevalence decreases. When a disease is rare in a population, a negative test result becomes even more reassuring because the baseline probability of disease was already low. Conversely, in high-prevalence settings, even a negative test carries more residual risk.

What is the difference between NPV and specificity?

Specificity measures how well a test identifies those without the disease (True Negatives ÷ (True Negatives + False Positives)) and is a fixed property of the test itself. NPV, however, depends on prevalence — the same test can have a different NPV in different populations.

When should I use the prevalence override field?

Use the prevalence override when your study sample is enriched or depleted for the disease compared to the real-world population. For example, if your study deliberately recruited equal numbers of diseased and non-diseased patients but true prevalence is 5%, entering 5% gives a more clinically meaningful NPV and PPV.

What are the Positive and Negative Likelihood Ratios?

LR+ (Sensitivity ÷ (1 − Specificity)) tells you how much a positive test result increases the odds of disease. LR− ((1 − Sensitivity) ÷ Specificity) tells you how much a negative test result decreases those odds. Values near 1 indicate the test provides little diagnostic information.

What is a good NPV value?

There is no universal threshold, but an NPV above 95% is generally considered strong for most clinical settings, meaning fewer than 5 in 100 people who test negative actually have the disease. The acceptable level depends on the severity of the condition and the consequences of a missed diagnosis.

How is PPV different from NPV?

PPV (Positive Predictive Value) is the probability that a positive test truly indicates disease, whereas NPV is the probability that a negative test truly rules out disease. Both depend on prevalence, and in low-prevalence settings PPV can be surprisingly low even for highly specific tests.

Can I use this calculator for COVID-19 or other screening tests?

Yes. Enter the observed counts of true positives, false negatives, false positives, and true negatives from your validation study. If the study population prevalence differs from the community you're screening, enter the real-world prevalence in the override field to get adjusted NPV and PPV estimates.

More Statistics Tools