I understand that a stationary time series is one whose mean and variance is constant over time. Can someone please explain why we have to make sure our data set is stationary before we can run different ARIMA or ARM models on it? Does this also apply to normal regression models where autocorrelation and/or time is not a factor? For example, when we predict revenue of next year, revenue does not depend on the past revenue itself, but the business activities. In this case, i don't think there is autocorrelation between time. Or i could be wrong, since i did some like this previously in my class, and my professor did not say i was wrong.
Asked
Active
Viewed 39 times
1
-
Related https://stats.stackexchange.com/questions/19715/why-does-a-time-series-have-to-be-stationary – spiridon_the_sun_rotator Jan 01 '21 at 07:41
-
Also related https://stats.stackexchange.com/questions/104977/consequences-of-modeling-a-non-stationary-process-using-arma – Sextus Empiricus Jan 01 '21 at 14:16