GREENCALC JOURNAL

Known Likelihood Ratio or Test Rates: Enter the Evidence You Have

Two input routes can describe the same update If sensitivity, specificity and the observed test result are known, the likelihood ratio can be derived from.

Two alternate blank evidence worksheets beside a neutral laboratory sample vial.
Known Likelihood Ratio or Test Rates: Enter the Evidence You Have — conceptual editorial illustration.

Two alternate blank evidence worksheets beside a neutral laboratory sample vial. Original AI-generated artwork produced for GreenCalc; not a measured diagram or empirical data display.

Image use and attribution

Two input routes can describe the same update

If sensitivity, specificity and the observed test result are known, the likelihood ratio can be derived from the corresponding result probabilities. If a likelihood ratio for that result is already supplied, it can be used directly with the pre-test odds. Both routes should agree when they represent the same population, protocol and evidence.

Compare a positive-result example

With sensitivity 90% and specificity 95%, LR+ = 0.9/0.05 = 18. A pre-test probability of 10% gives prior odds 1/9. Multiplying by 18 yields posterior odds 2, or probability 2/3. Entering LR = 18 directly in the Post-Test Probability Calculator should produce the same posterior as the rate-based positive-result route.

An LR does not supply every missing quantity

The positive-result probability in that rate model is 0.1×0.9+0.9×0.05 = 0.135. LR+ alone does not identify it: many different numerator and denominator likelihoods can share the same ratio. Accordingly, the tool does not invent an evidence probability in known-LR mode. It reports only quantities the inputs support.

Use the ratio for the evidence actually observed

For a negative result, use LR minus rather than applying LR plus to the opposite outcome. Read the negative-test worked example for that calculation. Repeated tests also require likelihoods conditional on earlier evidence if dependence exists; the existing sequential-evidence guide explains why marginal ratios cannot always be multiplied. This page focuses on input interpretation and does not determine which clinical test or action a person should choose.

Check the model behind your result

Use the Post-Test Probability Calculator for the supported calculation and review its stated assumptions before interpreting the output. Find related tools in the Statistics category, or browse the GreenCalc homepage for other calculation topics.

By GreenCalc Editorial Team · Updated 2026-10-26

Sources

How was this calculator?

Your email stays private. Comments are published after moderation.