Uno n subset, of the time series ibm, the columns Sales and Profita starting, in 1955 ending in 1990, to answer the following, questions, (a) Plot the ts, are there any unusual observations? Do you need to transform the data to stabilize the variance? (b) Is the data stationary? If yes, explain why, if no, perform the neces- sary transformations. (c) Use the VARselect function to determine the number of initial lags for your VAR model. (d) Estimate that model using VAR. Do you have white noise residuals? How do you know? If not, what steps do you need to take to improve the model? Take those steps. (Note it is possible that you don't find a model that has white noise residuals. If that's the case move forward forecasting your best fitting model.) (e) Forecast you time series 3 years ahead. Plot your forecasts. dothey seem reasonable? Why or why not? (hint, you can use the dillinv() function in R to undoany differences you may or may not have taken before plotting your forecasts.)