MediumProbabilitypr-176

P-hacking Detection Lite

Problem

Probability of at least one false positive across m independent hypothesis tests each run at significance level alpha:

FWER = 1 - (1 - alpha)^m.

This is the family-wise error rate that p-hacking inflates. Return 0.0 for invalid inputs.

Hint

Complement of all tests being non-significant.

case 1

in: [0.05,1]

expected: 0.050000000000000044

case 2

in: [0.05,20]

expected: 0.6415140775914581

case 3

in: [0.01,100]

expected: 0.6339676587267709

case 4

in: [0.05,0]

expected: 0

Starter codePython

def family_wise_error_rate(alpha, m):
    # Your code here
    pass

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