How do you make time series data stationary?

Conditions

• Used when data exhibits non-stationarity.

Reasoning, step by step

1. Identify the need for stationarity.
2. Apply differencing to the data.
3. Compute the differences between consecutive observations.

Example

Slide text states: 'Essentially, you need to make your data stationary (typically done through differencing).' Speaker says, 'Typically, we take differences in our data to make our data stationary.'

Common misconceptions

• Thinking that differencing changes the underlying distribution shape permanently.
• Believing that all time series require differencing.

Watch the explanation

Explore next

• What do the parameters p, d, and q represent in an ARIMA model?
• Can you show me an example of an ARIMA(1,1,1) model and its equations?