Source

Median Absolute Error#

Median Absolute Error (MAD) is a robust measure of error, similar to MAE, that ignores highly erroneous predictions. Because MAD is a robust statistic, it works well even when used to measure non-normal distributions.

Note: In order to maintain the convention of maximizing validation scores, this metric outputs the negative of the original score.

Estimator Compatibility: Regressor

Output Range: -∞ to 0

Example#

use Rubix\ML\CrossValidation\Metrics\MedianAbsoluteError;

$metric = new MedianAbsoluteError();