Beta-Binomial Posterior Mean

Problem

After observing successes successes in trials Bernoulli trials, a Beta(alpha, beta) prior updates to Beta(alpha + successes, beta + trials - successes), whose mean is (alpha + successes) / (alpha + beta + trials). Return that posterior mean, or 0.0 for invalid arguments.

Hint

Add the observed successes and failures to the two prior pseudo-counts.

Test cases

case 1

in: [1,1,3,10]

expected: 0.3333333333333333

case 2

in: [2,3,5,5]

expected: 0.7

case 3

in: [1,1,0,0]

expected: 0.5

case 4

in: [3,3,0,4]

expected: 0.3

case 5

in: [0,1,2,3]

expected: 0

Starter codePython

def beta_binomial_posterior_mean(alpha, beta, successes, trials):
    # Your code here
    pass

5 test cases · run your code against them in the editor