in R

$1-$Create a training set for $$Australian takeaway food$$ turnover $($aus$\_$retail$)$ by withholding the last four years as a test set.

$2-$Fit all the appropriate simple$/$benchmark forecasting methods to the training set and forecast the periods covered by the test set. Justify your model selection. $($You include any plots to justify your answer.$)$

$3-$Compute the accuracy of your forecasts based on RMSE, MAE, MAPE, and MASE. Which method does best? Explain your answer.

$4-$Do the residuals from the best method resemble white noise? Explain your answer.

$5-$Run Ljung$-$Box test with lag$=24$ to prove your answer in question $4.$

$6-$Extend the experiment for the best method you obtained in question $4$ with a cross$-$validation method. Stretch with a minimum length of $3,$ growing by $1$ each step. Use the same forecast horizon for the hold$-$out method. Evaluate the model using RMSE, MAE, MAPE, and MASE. Compare the results with the hold$-$out method. Which method give a better accuracy?