Abstract. The root-mean-squared error (RMSE) and mean absolute (MAE) are widely used metrics for evaluating models. Yet, there remains enduring confusion over their use, such that a standard practice is to present both, leaving it the reader decide which more relevant. In recent reprise 200-year debate Willmott Matsuura (2005) Chai Draxler (2014) give arguments favoring one metric or other. How...

We study in this paper the consequences of using the Mean Absolute Percentage Error (MAPE) as a measure of quality for regression models. We show that finding the best model under the MAPE is equivalent to doing weighted Mean Absolute Error (MAE) regression. We show that universal consistency of Empirical Risk Minimization remains possible using the MAPE instead of the MAE.

In this paper a new variation of the well known MAE (Mean Absolute Error) matching criterion for video coding applications, is introduced. The MAE criterion is simpler than the MSE criterion because of the lack of multiplication operations, but it achieves a lower performance in terms of PSNR and MSE. In this work we impose an additional statistical constraint over the MAE thus filling the perf...

–The aim of this paper is to evaluate the quality of object oriented modules. In this work neural network approach is used along with PSO (particle swarm optimization) to find out fault prone components of software. The evaluation measures used are Accuracy, MAE (Mean absolute error), RMSE (Root mean square error) and the results are calculated on different iterations. The Accuracy, MAE, RMSE i...

Here, we document the performance of different DFT and DFTB methods with respect to the C−O stretch vibration, both in terms of absolute frequencies and effects of hydrogen bonds on the frequencies. We demonstrate, that PBE/def2-TZVP is a suitable reference for the C−O stretch frequency in carboxylic acids. In the following text, the abbreviations ME (mean error), MAE (mean absolute error), MSE...

in this research, the spatial distribution of fe, cu, zn and mn on agricultural lands of golestan province were evaluated using different interpolation methods such as, kriging, inverse distance weighted, local polynomial, inverse multiquadric and radial basis function. thus, 505 soil samples were provided from fields during 2008 and micronutrients rates were measured for each sample. the perfo...

The focus of this paper is to construct daily time series exchange rate forecast models of Samoan Tala/USD and Tala/AUD during the year 2008 to 2012 with neural network The performance of the models was measured by using varies error functions such as Root Square mean error (RSME), Mean absolute error (MAE), and Mean absolute percentage error (MAPE). Our empirical findings suggest that AR (1) m...