Let's say you have some time series data that you think exhibits a drift, but you are unsure. Is it better to test first a regression with a drift and a trend to see if that is stationary?
Secondly, if it is stationary, then you know the drift is also stationary. If it is not stationary, then check only the regression with a drift.
Just looking for some guidance about how to approach and generalize the process for intermediate people like myself.