Ambiguities inherent in sums-of-squares-based error statistics

By Cort J. Willmott, Kenji Matsuura, Scott M. Robeson. 2009

224 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b1b7d0aae076640f9c74ebf831b236779d03edb4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

Citations in the corpus

A refined index of model performance (2012, background): “Our experience has been that average-error or- deviation measures that are based on absolute values of differences – like the mean-absolute error (MAE) and mean-absolute deviation (MAD) – are, in general, preferable to those based on squared differences, like the root-mean-squared error (RMSE) (Will”
On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression (2020, background): “Another form of average error is a root-mean-squared error (RMSE), but MAE was shown to outperform RMSE for measuring an average model accuracy in most situations except the Gaussian noisy scenarios [3]–[5].”
A survey on missing data in machine learning (2021, methodology): “The authors further advised against the reporting of RMSE in literature and strongly recommended the use of MAE [146, 150].”
Root mean square error (RMSE) or mean absolute error (MAE)? – Arguments against avoiding RMSE in the literature (2014, background): “Fortunately, there are often hundreds of observations available to calculate model statistics, unlike the examples with n= 4 (Willmott and Matsuura, 2005) and n= 10 (Willmott et al., 2009).”
Root mean square error (RMSE) or mean absolute error (MAE) (2014, methodology): “While some concerns over using RMSE raised by Willmott and Matsuura (2005) and Willmott et al. (2009) are valid, the proposed avoidance of RMSE in favor of MAE is not the solution. Citing the aforementioned papers, many researchers chose MAE over RMSE to present their model evaluation statistics whe”