A Beta distribution represents uncertainty about an unknown probability θ, which lies between 0 and 1. Its two positive shape parameters, a and β, can be read as prior pseudocounts: successes and failures. Its mean is a/(a + β). section 7.4.2
This notation specifies θ’s prior distribution and its two shape parameters. section 7.4.2
Paired with a Binomial likelihood, the Beta distribution is conjugate: the posterior remains Beta, with parameters updated by adding observed successes and failures to the prior pseudocounts. section 7.4.2
Estimating a machine’s defect rate
A prior Beta(1, 19) represents an expected defect rate of 5%. After inspecting 10 parts and finding 2 defects, the posterior is Beta(3, 27), with mean 10%; the observed sample rate is 20%. section 7.4.2



