Beta distributions
The beta distribution is a distribution of probabilities that models the uncertainty about the probability of success of an experiment. There are only two outcomes in the beta distribution – “yes” and “no.” We just do not know the actual probability of “yes” or “no” in an experiment. However, we may have prior knowledge to guess their probability. Let’s see a real-world example.
The real-world examples
Suppose you are at a table in a casino that bets on flipping coins. Assume you do not know the probability of whether the coin is 1 = head and 0 = tail, and you do not believe it is a fair coin. You had heard from others that the probability of the unfair coin is 0.52 for 1 = head and 0.48 for 0 = tail. The 0.52 or 0.48 is your “prior belief” in the Bayesian terminology. The outcomes of the coin for “1 = head” in multiple experiments can range from 0.35 to 0.85,...
