Geoscientific Model Development
Geoscientific Model Development
GMD
Articles | Volume 15, issue 14
Articles | Volume 15, issue 14
https://doi.org/10.5194/gmd-15-5481-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/gmd-15-5481-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 15, issue 14
Review and perspective paper
 | Highlight paper
 | 
19 Jul 2022
Review and perspective paper | Highlight paper |  | 19 Jul 2022

Root-mean-square error (RMSE) or mean absolute error (MAE): when to use them or not

Timothy O. Hodson

Cited articles

Bernoulli, J.: Ars conjectandi: Usum & applicationem praecedentis doctrinae in civilibus, Moralibus & Oeconomicis, 4, 1713, 1713. a
Boscovich, R. J.: De litteraria expeditione per pontificiam ditionem, et synopsis amplioris operis, ac habentur plura ejus ex exemplaria etiam sensorum impessa, Bononiensi Scientiarum et Artum Instuto Atque Academia Commentarii, 4, 353–396, 1757. a
Box, G. E. and Cox, D. R.: An analysis of transformations, J. Roy. Stat. Soc. B Met., 26, 211–243, 1964. a
Burnham, K. P. and Anderson, D. R.: Kullback–Leibler information as a basis for strong inference in ecological studies, Wildlife Res., 28, 111, https://doi.org/10.1071/wr99107, 2001. a, b, c, d, e
Chai, T. and Draxler, R. R.: Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature, Geosci. Model Dev., 7, 1247–1250, https://doi.org/10.5194/gmd-7-1247-2014, 2014. a, b, c, d, e, f, g
More articles (26)
Download
Editorial statement
This is a beautifully written exposition of the properties of two key statistics used in the evalution of models. Everyone working with models should read this paper.
Read more
Short summary
The task of evaluating competing models is fundamental to science. Models are evaluated based on an objective function, the choice of which ultimately influences what scientists learn from their observations. The mean absolute error (MAE) and root-mean-squared error (RMSE) are two such functions. Both are widely used, yet there remains enduring confusion over their use. This article reviews the theoretical justification behind their usage, as well as alternatives for when they are not suitable.
Read more
Share