I have couple of questions in timeseries forecasting.
If the timeseries is non-stationary, should we make it to stationary for running auto.arima OR this function automatically convert it?
How to optimise the auto.arima?
If we take log of timeseries to make it stationary, the forecasted values are in the log format.
How do we convert them to the original scale?
When to choose auto.arima and when to use ets()?
Thanks in advance,