Which one of the following is not a step in cross-validation with time series? A) Use both the training and validation set to re-estimate the preferred model. B) Split data series into early and later periods, representing both training and validation set. C) Determine the proper forecast model based on R²results. D) Explore suitable forecasting models to compute MSE, MAD, and MAPE.

Question

Quizplus · Accepted Answer

Cross-validation with time series typically does not involve determining the proper forecast model based on specific results like "R²," which seems to be a nonsensical or highly specific notation not generally associated with the cross-validation process. Cross-validation steps usually involve splitting the data, exploring forecasting models, and re-estimating the model using different subsets of the data.

Which One of the Following Is Not a Step in Cross-Validation