powered by
`nmse()` computes the Normalized Mean Squared Error between the output of a regression model and the actual values of the target.
nmse(target, pred)
The normalized mean squared error (a single value).
Numeric vector containing the actual values.
Numeric vector containing the predicted values. (The order should be the same than in the target)
The Normalized Mean Squared error is defined as:
$$NMSE=MSE/((N-1)*var(target))$$
where MSE is the Mean Squared Error.
y <- 1:10 y_pred <- y+rnorm(10) nmse(y,y_pred)
Run the code above in your browser using DataLab