BIC Prior Term

Problem

Return the parameter-complexity term of the Bayesian information criterion:

penalty = k * ln(n)

where k is the number of parameters and n the number of samples. This term approximates the volume of the parameter prior.

Hint

Unlike AIC, the BIC penalty grows with the sample size.

case 1

in: [1,8]

expected: 2.0794415416798357

case 2

in: [2,16]

expected: 5.545177444479562

case 3

in: [3,100]

expected: 13.815510557964275

case 4

in: [0,10]

expected: 0

Starter codePython

import math
def bic_prior_term(k, n):
    # Your code here
    pass

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