Mean Bias Error

The mean bias error (MBE) is a measure of how closely a set of predicted values match the set of observed or true values. Windographer calculates MBE using the following equation:

where:

N   is the number of values in the set
yi is the ith observed value
is the ith predicted value

The MBE is equal to the mean of the predicted values minus the observed values. It measures the mean bias in the predictions.

See also

Mean Absolute Error definition

Root Mean Squared Error definition

Forecast Error Window

Algorithm Performance Test Window


Written by: Tom Lambert
Contact: windographer.support@ul.com
Last modified: August 6, 2020