Block Bootstrap Standard Error

Problem

Return the block bootstrap standard error of the mean: split data into non-overlapping blocks of length block_len, resample the blocks with replacement using the seeded Lehmer RNG, and return the population standard deviation of the resample means. Return 0.0 when data is empty, n_boot <= 0, or block_len is not in [1, n].

Hint

Whole blocks preserve short-range dependence.

Test cases

case 1

in: [[1,2,3,4,5,6],2,200,7]

expected: 0.9854440623394105

case 2

in: [[1,2,3,4,5],2,300,42]

expected: 0.6925315877272313

case 3

in: [[5,5,5,5],2,100,1]

expected: 0

case 4

in: [[1,2,3],5,100,1]

expected: 0

case 5

in: [[],2,100,1]

expected: 0

Starter codePython

def block_bootstrap_se(data, block_len, n_boot, seed):
    # Your code here
    pass

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