Errors and Residuals

What is the difference between an error and a residual?

Answer

An error (unobservable) is the difference between the observed value \( Y \) and the true value \( f(X) \).

\[ \varepsilon = Y - f(X) \]

A residual (observable) is the difference between the observed value \( Y \) and the predicted value \( \hat{f}(X) \) given by the model.

\[ r = Y - \hat{f}(X) \]
Back to collection