Breusch-Pagan Lite

Problem

Return the Pearson correlation between x and the squared residuals, a quick heteroscedasticity indicator. Return 0.0 when fewer than two points are given or either variable has zero variance.

Hint

A strong correlation suggests the error variance changes with x.

Test cases

case 1

in: [[1,2,3,4],[1,4,9,16]]

expected: 0.9163023485215754

case 2

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

expected: 0

case 3

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

expected: 0

case 4

in: [[1,2,3,4],[4,9,16,25]]

expected: 0.9461581522243414

case 5

in: [[1,2],[1,4]]

expected: 1

Starter codePython

def breusch_pagan_lite(x, residuals):
    # Your code here
    pass

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