Before fitting any existing model to time-series data we check for different things

- Stationarity of time series: Stationarity of time series is ensured by three properties [1]. A pictorial depiction of these properties is shown at link
- The mean of time-series (
*x*) is the same for all_{t}*x*._{t} - The variance of time-series (
*x*) is the same for all_{t}*x*._{t} - The covariance (and also correlation) between
*x*and_{t}*x*is the same for all_{t-h}*t*.

- The mean of time-series (

We care about stationarity because most time-series models assume stationarity. Also, a time-series can be stationarized by detrending and differencing.

References :

- https://onlinecourses.science.psu.edu/stat510/node/60
- http://www.analyticsvidhya.com/blog/2015/12/complete-tutorial-time-series-modeling/

Advertisements