Lag Selection Autocorr

Problem

Select the lag with the strongest absolute sample autocorrelation for lags 1..max_lag, using the biased estimator. Ties keep the smallest lag.

Return 1 when the series is constant (zero variance); return 0 for fewer than three points or max_lag < 1.

Hint

The strongest autocorrelation suggests the most useful lagged input.

case 1

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

expected: 1

case 2

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

expected: 1

case 3

in: [[5,5,5,5],3]

expected: 1

case 4

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

expected: 2

Starter codePython

def lag_selection_autocorr(series, max_lag):
    # Your code here
    pass

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