Leave-one-out CV Error For ridge regression model, y = Sy, where S = X(X X + Alp) 1X and y is the vector of n observations. The definitions of the notations are the same as in the textbook. Show that the leave-one- out cross-validation error is yi - y-i(xi) = yi - yi 1 - Sii where yi(xi) is the prediction at xi using the model fitted by all the data except (xi, yi), yi is the prediction at xi using the model fitted by all the data, and Si is the ith diagonal entry of S

Answer rating: 100% (QA)

The Answer is in the image, click to view ... View the full answer