In k-fold cross-validation, the model is fitted a total of k times.

In k-fold cross-validation, the model is fitted a total of k times.

• A. True
• B. False
• C. It depends on the dataset size
• D. It depends on the number of folds

Answer: (A)

In k-fold cross-validation you create k separate train-test splits and fit the model once for each split. Specifically, you train on k−1 folds and evaluate on the remaining fold, repeating this process for all k folds. This means you fit the model k times in total. A helpful edge case: in leave-one-out cross-validation, k equals the number of observations, so you still fit the model n times, which is consistent with the general idea. Therefore, the statement is true.

In k-fold cross-validation you create k separate train-test splits and fit the model once for each split. Specifically, you train on k−1 folds and evaluate on the remaining fold, repeating this process for all k folds. This means you fit the model k times in total. A helpful edge case: in leave-one-out cross-validation, k equals the number of observations, so you still fit the model n times, which is consistent with the general idea. Therefore, the statement is true.