In Bayesian reasoning this is the probability calculated after combining fresh evidence with the prior distribution. It is given by Bayes rule: Posterior(A_{f}|E) = P(E|A_{f})xPrior(A_{f})/(Σ_{all i} P(E|A_{i})xPrior(A_{i})), where E is the evidence, and A_{i} ranges over all alternatives including the focus one A_{f}. Note that in Bayesian statistics the posterior distribution is typically not a real probability but a quantified belief or plausibility.

Defined on page 71

Used on pages 71, 72, 75, 76, 77, 78, 81, 85, 86, 87, 142

Also known as Bayesian posterior probability, posterior, posterior probabilities, posterior probability, posterior probability distribution