Skip to content

IAI Actuarial Core Principles · Risk Modelling and Survival Analysis · Elementary principles of machine learning

In 5-fold cross-validation on 500 observations used to compare two regularised regression models, which statement is correct?

In 5-fold cross-validation each observation is in the validation fold exactly once and in the training set for the other four fits. Each fit trains on 400 observations and validates on 100, and the five errors are averaged.

  1. AEach observation is used for validation exactly once and for training four timesCorrect
  2. BEach model is fitted once using 100 observations only
  3. CThe test error is computed on the training folds
  4. DEach observation is used for validation five times
  5. Only 100 observations are ever used for training

Explanation

Data are split into 5 folds of 100. Each fold is held out once for validation while the other four (400 observations) train the model. So every observation validates once and trains in the other four fits. The error estimates are averaged across folds.

Did you get it right without looking?

One question tells you little. A timed set on Elementary principles of machine learning shows your real accuracy, how long you take and where you lose marks.

Practise Elementary principles of machine learningFree diagnostic mock

More Elementary principles of machine learning questions