Part of the Math & Statistics suite · 235 calculators

Post-Test Probability Calculator

Update a probability with a likelihood ratio — the odds form of Bayes' theorem, and the fastest way to see what a test result is actually worth.

Work in odds, not probabilities: post-test odds = pre-test odds × likelihood ratio.

%
Results update as you type
Results
Post-test probability
71.4286%
Pre-test odds
Post-test odds
Change in probability
Strength of the evidence
People to test to change one mind
Reviewed September 2026. Pure mathematics: the result does not depend on where you are. Terminology follows US usage (math, parentheses, decimal point).
No account required · Google Analytics off unless allowedCalculator arithmetic runs in your browserResults update as you type
All calculations run 100% in your browser. The calculator code does not submit your figures to GlobalCalc to obtain a result.
About post-test probability

How the post-test probability calculator works

Work in odds, not probabilities: post-test odds = pre-test odds × likelihood ratio. Convert the prior to odds, multiply, convert back. That is the whole calculation, and it is why likelihood ratios are the natural currency of diagnostic evidence.

A likelihood ratio of 1 changes nothing. Above 10 or below 0.1 is a decisive result; between 0.5 and 2 is barely worth the sample.

Formula: post-test odds = pre-test odds × LR; p = odds / (1 + odds)

Worked examples

InputsPost-test probabilityNote
20% prior, LR 1071.4286%rises to 71.4%
A negative result: LR 0.12.439%falls to 2.4%
An uninformative test: LR 120%unchanged at 20%

Frequently asked questions

What is a likelihood ratio?

How many times more likely this result is in someone with the condition than without. LR+ = sensitivity ÷ (1 − specificity).

Why work in odds?

Because Bayes' theorem is a plain multiplication in odds and a messy fraction in probabilities.

What counts as a good test?

LR above 10 or below 0.1 shifts the probability decisively. Between 0.5 and 2, the result barely matters.

Can a test make something certain?

No. A finite likelihood ratio can never move a probability all the way to 0 or 100%.

Does the prior really matter that much?

Enormously. The same LR of 10 takes a 1% prior to 9% and a 50% prior to 91%. This is why testing a low-risk population produces mostly false positives.

Where these figures come from

Last checked: September 2026. Formulas are fixed by mathematics and do not change with tax years or regulations.