Free · Physical and mathematical models

Sensitivity, Specificity and Likelihood Ratios

Summarize binary classification counts and use a specified prevalence to calculate predictive probabilities.

  • Formula & worked example
  • Private in your browser
  • No signup
Go to tool

Calculator inputs

Loading calculator…

How to use this calculator

  1. Enter the known values in the units shown. Results update as you type.
  2. Where results are editable, change one to solve backwards. Lock a value to hold it fixed.
  3. Use the worked example to check the method. Reset restores the starting fields.

Private by default

Inputs and results stay in this browser tab. Bookify does not upload or store the values you enter.

Formula and method

Summarize binary classification counts and use a specified prevalence to calculate predictive probabilities.

sensitivity=TP/(TP+FN); specificity=TN/(TN+FP); predictive values follow Bayes’ rule

Worked example

Enter these known values and leave the other values blank.

True positive
40
True negative
40
False positive
10
False negative
10
Prevalence
50 %
Sensitivity
80 %
Specificity
80 %
Positive likelihood ratio
4
Negative likelihood ratio
0.25
Positive predictive value (PPV)
80 %
Negative predictive value (NPV)
80 %
Accuracy
80 %

Assumptions and limitations

  • This is hypothetical binary classification arithmetic. It does not diagnose an individual or establish that a test or classifier is suitable for a setting.
  • Counts are nonnegative integers, with positive true-positive and true-negative counts in the retained model. Prevalence is the proportion with the condition in the target population.
  • Predictive values depend on the supplied prevalence. Changing prevalence need not alter sensitivity or specificity.
  • Singular likelihood-ratio endpoints cannot yield finite ratios; clearing a value leaves an incomplete calculation.

Common questions

How should I use an inverse?

Leave the required unknown empty and supply compatible known values. Multiple mathematical solutions or zero denominators can prevent a unique inverse.

What does this model assume?

This is hypothetical binary classification arithmetic. It does not diagnose an individual or establish that a test or classifier is suitable for a setting.

References

Replace explanatory external images with original accessible descriptions preserving every image condition and control relationship. Require integer classification counts so retained diagnostic count formulas cannot accept fractional people or observations.

Explore physical and mathematical models or browse all statistics calculators.