Statistical Significance Bootstrap

Problem

Compute a seeded bootstrap confidence interval for the mean.

With rng = random.Random(seed), draw n_resamples bootstrap samples of the same size as scores using rng.randrange(n), average each, sort the means, and return [means[int(0.025 * n_resamples)], means[int(0.975 * n_resamples)]]. An empty input returns [0.0, 0.0].

Hint

Bootstrapping builds the sampling distribution of the mean by resampling with replacement.

Test cases

case 1

in: [[1,2,3,4,5],200,0]

expected: [1.8,4.4]

case 2

in: [[0.5,0.5],100,7]

expected: [0.5,0.5]

case 3

in: [[],50,0]

expected: [0,0]

case 4

in: [[10],50,42]

expected: [10,10]

Starter codePython

import random
def bootstrap_ci(scores, n_resamples, seed):
    # Your code here
    pass

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