CUSUM Reset Statistic

Problem

Compute the peak of a one-sided upper CUSUM with reset. For each observation update S = max(0, S + x - target - k) and track the largest S reached.

This detects persistent upward shifts relative to the target, with k the reference slack.

Hint

The reset to zero makes small deviations decay while sustained shifts accumulate.

case 1

in: [[1,2,1,3,1],0,0.5]

expected: 5.5

case 2

in: [[0.1,0.1],0,0.5]

expected: 0

case 3

in: [[5,5,5],5,0]

expected: 0

case 4

in: [[2,4,6,8],3,1]

expected: 6

Starter codePython

def cusum_reset_statistic(series, target, k):
    # Your code here
    pass

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