Question

How would stationarity be corrected in time series analysis if present? You need not conduct this correction, simply discuss it.

Answer 1

A stationary time series is one whose statistical properties such as mean, variance, autocorrelation etc., are constant over time. A non-stationary series is one whose statistical properties change over time. Time series data sets may contain trends and seasonality which are removed prior modelling. We can check our time series is stationary by analyzing plot of the series over time. More accurate method is to use a statistical test, such as the Dickey - Fuller test. If we have clear trend and seasonality in our time series, we model these components, remove them from observations and then train models on the residuals.