mrae {bvhar} | R Documentation |
Evaluate the Model Based on MRAE (Mean Relative Absolute Error)
Description
This function computes MRAE given prediction result versus evaluation set.
Usage
mrae(x, pred_bench, y, ...)
## S3 method for class 'predbvhar'
mrae(x, pred_bench, y, ...)
## S3 method for class 'bvharcv'
mrae(x, pred_bench, y, ...)
Arguments
x |
Forecasting object to use |
pred_bench |
The same forecasting object from benchmark model |
y |
Test data to be compared. should be the same format with the train data. |
... |
not used |
Details
Let .
MRAE implements benchmark model as scaling method.
Relative error is defined by
where is the error from the benchmark method.
Then
Value
MRAE vector corresponding to each variable.
References
Hyndman, R. J., & Koehler, A. B. (2006). Another look at measures of forecast accuracy. International Journal of Forecasting, 22(4), 679–688.
[Package bvhar version 2.0.1 Index]