Another approach of solving the problem of inconsistent signs of error is to square the error (the square of a negative number is a positive number). The scenario discussed previously can be translated as follows:
|
|
Actual value |
Predicted value |
Error |
Squared error |
|
Data point 1 |
100 |
120 |
20 |
400 |
|
Data point 2 |
100 |
80 |
-20 |
400 |
|
Overall |
200 |
200 |
0 |
800 |
In this case, the overall squared error is 800 and root mean squared error is the square root of (800/2), which is 20.
The accuracy in the case of a classification exercise is measured as follows: absolute error and RMSE are applicable when predicting continuous variables. However, predicting an event with discrete outcomes is ...
