The correct answer is: D. mean positive error.
Mean positive error is the average of the absolute values of the positive differences between computed and desired outcome values. It is a measure of the average amount by which the computed values are too high.
Root mean squared error (RMSE) is the square root of the mean squared error. It is a measure of the average squared difference between computed and desired outcome values.
Mean squared error (MSE) is the average of the squared differences between computed and desired outcome values. It is a measure of the average squared error between the computed values and the desired values.
Mean absolute error (MAE) is the average of the absolute values of the differences between computed and desired outcome values. It is a measure of the average absolute error between the computed values and the desired values.
Here is a table that summarizes the differences between the four measures:
| Measure | Formula | Interpretation |
|—|—|—|
| Root mean squared error (RMSE) | $\sqrt{\frac{\sum_{i=1}^n (y_i – \hat{y}i)^2}{n}}$ | The square root of the mean squared error. It is a measure of the average squared error between the computed values and the desired values. |
| Mean squared error (MSE) | $\frac{\sum{i=1}^n (y_i – \hat{y}i)^2}{n}$ | The average of the squared differences between the computed and desired outcome values. It is a measure of the average squared error between the computed values and the desired values. |
| Mean absolute error (MAE) | $\frac{\sum{i=1}^n |y_i – \hat{y}i|}{n}$ | The average of the absolute values of the differences between the computed and desired outcome values. It is a measure of the average absolute error between the computed values and the desired values. |
| Mean positive error (MPE) | $\frac{\sum{i=1}^n |y_i – \hat{y}i|}{n} \cdot \frac{1}{n} \sum{i=1}^n \mathbb{I}(y_i – \hat{y}_i > 0)$ | The average of the absolute values of the positive differences between the computed and desired outcome values. It is a measure of the average amount by which the computed values are too high. |