Primary formula
P(A|B)=P(B|A)P(A)/P(B), where P(B) can be entered or expanded across A and not A.
Statistics calculator
Bayes Theorem Calculator
Update a prior probability after evidence and inspect the numerator, evidence denominator and posterior.
Last reviewed: August 6, 2026Statistics calculation engine v2.0.0
Bayes Theorem Calculator
Update a prior probability after evidence and inspect the numerator, evidence denominator and posterior.
Formula and assumptions
Input assumptions
All probabilities refer to compatible events. The evidence denominator includes relevant branches. Diagnostic mode is educational and not a medical diagnosis.
Precision note
Statistics calculations use Decimal.js for deterministic arithmetic; displayed values are rounded only after the selected method is evaluated.
How NexaCalc evaluates the inputs
Parse
Finite numeric observations and method-specific inputs are validated locally.
Calculate
The selected Statistics method runs in a pure TypeScript engine.
Explain
The result includes substitutions, ordered data, supporting measures and method warnings.
Visualize
A tool-specific dataset visual appears only after a valid calculation.
What the Bayes Theorem Calculator does
Use this Statistics page to apply Bayes theorem without hiding base rates or likelihood assumptions.
Bayes Theorem Calculator processes the entered values locally and exposes the selected convention, calculation steps and related values.
When to use the Bayes Theorem Calculator
Use this Statistics page to apply Bayes theorem without hiding base rates or likelihood assumptions.
Choose the mode that matches the data available and the question being answered before entering values.
Formula, variables and units
P(A|B)=P(B|A)P(A)/P(B), where P(B) can be entered or expanded across A and not A.
- P(A) is the prior.
- P(B|A) is the evidence likelihood under A.
- P(B) is the total evidence probability and P(A|B) is the posterior.
Statistical assumptions
The calculation is deterministic, but interpretation depends on whether the selected model and entered data fit the real situation.
- All probabilities refer to compatible events.
- The evidence denominator includes relevant branches.
- Diagnostic mode is educational and not a medical diagnosis.
Step-by-step worked example
Use the default example inputs to reproduce the primary worked example. The result breakdown is produced by the same pure TypeScript engine used by the page.
- Prior 0.01, sensitivity 0.9 and false-positive rate 0.05 give evidence 0.0585.
- The corresponding posterior is about 0.153846.
- Direct prior 0.2, likelihood 0.7 and evidence 0.4 gives posterior 0.35.
Additional examples and interpretation
The following examples show how data, event structure, count or method changes the result.
- Prior 0.01, sensitivity 0.9 and false-positive rate 0.05 give evidence 0.0585.
- The corresponding posterior is about 0.153846.
- Direct prior 0.2, likelihood 0.7 and evidence 0.4 gives posterior 0.35.
Concept explanation
Bayes theorem reverses a conditional direction by combining a prior with evidence likelihoods.
The denominator normalizes all routes that can produce the observed evidence, which is why base rates can materially affect the posterior.
How to read the statistics visual
The dynamic visual is a prior and complement probability tree normalized into a posterior. It appears only after a valid calculation and uses the current result.
Visual proportions are normalized for readability and are explanatory rather than a substitute for a full statistical plot.
Common mistakes
Check dataset parsing, method choice and denominator before using a result.
- Ignoring the base rate.
- Confusing P(B|A) with P(A|B).
- Using specificity as the false-positive rate instead of 1-specificity.
Limitations and method-choice notes
Statistical conventions and model assumptions can change a result or its interpretation.
- Weak priors or likelihood estimates produce weak posteriors.
- Bayes arithmetic cannot correct biased data or missing hypotheses.
Educational and privacy note
This calculator provides educational statistics calculations and does not replace statistical consulting, instructor guidance or professional analysis.
Input values are processed in the browser calculator session and are not sent to an external statistics service.
Frequently asked questions
What does the Bayes Theorem Calculator calculate?
It returns the posterior probability after normalizing evidence across the entered branches.
What inputs does the Bayes Theorem Calculator require?
a prior, likelihood and either evidence, a complementary likelihood, or sensitivity and specificity
Which formula does the Bayes Theorem Calculator use?
P(A|B)=P(B|A)P(A)/P(B)
How should I interpret the Bayes Theorem Calculator result?
It returns the posterior probability after normalizing evidence across the entered branches. Interpret it only under the assumptions stated on the page.
What assumptions are important for the Bayes Theorem Calculator?
A posterior is only as credible as its prior, likelihood model and evidence definition; diagnostic mode is educational only.
What common mistake should I avoid in the Bayes Theorem Calculator?
Select the mode that matches the question, keep units or probabilities consistent and do not treat a model output as stronger evidence than the inputs support.
How does the Bayes Theorem Calculator differ from the Probability Calculator?
The tools answer related but different questions. The Bayes Theorem Calculator follows P(A|B)=P(B|A)P(A)/P(B), while the Probability Calculator reports its own named quantity or model.
Can I use decimal values in the Bayes Theorem Calculator?
Yes where the selected model permits them. Whole-number count fields reject decimals, while measurements, probabilities and dataset values accept finite decimals.
Does the Bayes Theorem Calculator prove a statistical conclusion?
No. It performs a deterministic calculation; study design, data quality and subject-matter interpretation remain separate.
How does the Bayes Theorem Calculator visual help?
The visual uses the current inputs and result to show the model structure, selected region or interval. It appears only after a valid calculation.
Why might another Bayes Theorem Calculator return a different value?
Different conventions, critical values, rounding rules or event assumptions can change results. NexaCalc labels the selected method and rounds only for display.
What are the main limitations of the Bayes Theorem Calculator?
A posterior is only as credible as its prior, likelihood model and evidence definition; diagnostic mode is educational only.
References
- OpenStax Introductory Statistics 2e, Measures of the Center of the Data. Relevance: mean, median and mode. Last verified: August 5, 2026. Source.
- OpenStax Introductory Statistics 2e, Measures of the Spread of the Data. Relevance: range, variance and standard deviation. Last verified: August 5, 2026. Source.
- NIST/SEMATECH e-Handbook, Measures of Scale. Relevance: statistical spread and scale measures. Last verified: August 5, 2026. Source.
- NIST/SEMATECH e-Handbook, Percentiles. Relevance: ordered data, ranks and percentile-method differences. Last verified: August 5, 2026. Source.
- OpenStax Introductory Statistics 2e, Two Basic Rules of Probability. Relevance: conditional, multiplication and addition rules. Last verified: August 6, 2026. Source.
- OpenStax Introductory Statistics 2e, Poisson Distribution. Relevance: discrete event-count probability models. Last verified: August 6, 2026. Source.
- OpenStax Introductory Statistics 2e, Confidence Intervals chapter review. Relevance: interval estimation, margin of error and sample size. Last verified: August 6, 2026. Source.
Statistics methods and references reviewed on August 6, 2026.
Educational disclaimer
This calculator provides mathematical results from the values, conventions and methods you enter. Verify important academic, engineering or professional work independently.