Mean Absolute Error (MAE)
An average of the absolute errors |ei| = |yi| - |xi|, where yi is the prediction and xi the true value.
Marcus Kelly avatar
Written by Marcus Kelly
Updated over a week ago

The mean absolute error is an average of the absolute errors |ei| = |yi| - |xi|, where yi is the prediction and xi the true value. The mean absolute error is given by:

The mean absolute error is a common measure of forecast error in time series analysis.

Did this answer your question?