What does it mean to say that the Beta distribution family is a conjugate prior for the Binomial distribution?
  • It means the following: if the prior belief in a Binomial parameter is described by a Beta distribution, then the posterior belief after observing a sample (generated from the Binomial distribution) will also have a Beta distribution, perhaps with a new set of hyperparameters. This property makes conjugate priors very convenient for mathematical manipulations.

Valid HTML 4.0 Transitional