Exercise

# AR or MA

In this exercise you will use the ACF and PACF to decide whether some data is best suited to an MA model or an AR model. Remember that selecting the right model order is of great importance to our predictions.

Remember that for different types of models we expect the following behavior in the ACF and PACF:

AR(p) | MA(q) | ARMA(p,q) | |
---|---|---|---|

ACF | Tails off | Cuts off after lag q | Tails off |

PACF | Cuts off after lag p | Tails off | Tails off |

A time series with unknown properties, `df`

is available for you in your environment.

Instructions 1/2

**undefined XP**

- Import the
`plot_acf`

and`plot_pacf`

functions from statsmodels. - Plot the ACF and the PACF for the series
`df`

for the first 10 lags but not the zeroth lag.