Skip to main content

Table 8 Used prediction accuracy measures

From: Prediction accuracy measurements as a fitness function for software effort estimation

ID Name Equations
1 Least absolute deviations (LAD) \(LAD=\sum \limits _{i=1}^{n}\left| y_i-\hat{y}_i\right|\)
2 Mean absolute error (MAE) \(MAE=\frac{1}{n}\sum \limits _{i=1}^{n}\left| y_i-\hat{y}_i\right|\)
3 Mean squared error (MSE) \(MSE=\frac{1}{n}\sum \limits _{i=1}^{n}\left( y_i-\hat{y}_i\right) ^2\)
4 Root mean squared error (RMSE) \(RMSE=\sqrt{\frac{1}{n}\sum \limits _{i=1}^{n}\left( y_i-\hat{y}_i\right) ^2}\)
5 Mean magnitude of relative error (MMRE) \(MMRE=\frac{1}{n}\sum \limits _{i=1}^{n}\frac{\left| y_i-\hat{y}_i\right| }{y_i}\)
6 Median magnitude of relative error (MdMRE) \(MdMRE=median\left( \frac{1}{n}\sum \limits _{i=1}^{n}\frac{\left| y_i-\hat{y}_i\right| }{y_i}\right)\)
7 MMRE relative to the estimate (MEMRE) \(MEMRE\,=\,\frac{1}{n}\sum \limits _{i=1}^{n}\frac{\left| y_i-\hat{y}_i\right| }{\hat{y}_i}\)
8 MdMRE relative to the estimate (MdEMRE) \(MdEMRE\,=\,median\left( \frac{1}{n}\sum \limits _{i=1}^{n}\frac{\left| y_i-\hat{y}_i\right| }{\hat{y}_i}\right)\)
9 R squared (\(R^2\)) \(R^2=1-\frac{\sum \limits _{i\,=\,1}^{n}\left( y_i-\hat{y}_i\right) ^2}{\sum \limits _{i=1}^{n}\left( y_i-\bar{y}\right) ^2}\)
10 Prediction within 25 % Pred(25) \(Pred(25)=\frac{Number\;of\;projects,\;where\;(MRE\le 0.25)}{Number\;of\;projects}\)