Get startedGet started for free

Identification

In the following exercises you will apply to the Box-Jenkins methodology to go from an unknown dataset to a model which is ready to make forecasts.

You will be using a new time series. This is the personal savings as % of disposable income 1955-1979 in the US.

The first step of the Box-Jenkins methodology is Identification. In this exercise you will use the tools at your disposal to test whether this new time series is stationary.

The time series has been loaded in as a DataFrame savings and the adfuller() function has been imported.

This exercise is part of the course

ARIMA Models in Python

View Course

Exercise instructions

  • Plot the time series using the DataFrame's .plot() method.
  • Apply the Dicky-Fuller test to the 'savings' column of the savings DataFrame and assign the test outcome to result.
  • Print the Dicky-Fuller test statistics and the associated p-value.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Plot time series
____
plt.show()

# Run Dicky-Fuller test
result = ____

# Print test statistic
____

# Print p-value
____
Edit and Run Code