Exercise

Data analysis - unemployment II

Now, you will continue fitting an SARIMA model to the monthly US unemployment unemp time series by looking at the sample ACF and PACF of the fully differenced series.

Note that the lag axis in the sample P/ACF plot is in terms of years. Thus, lags 1, 2, 3, … represent 1 year (12 months), 2 years (24 months), 3 years (36 months), …

Once again, the astsa package has been pre-loaded for you.

Instructions

100 XP
  • Difference the data fully (as in the previous exercise) and plot the sample ACF and PACF of the transformed data to lag 60 months (5 years). Consider that, for
    • the nonseasonal component: the PACF cuts off at lag 2 and the ACF tails off.
    • the seasonal component: the ACF cuts off at lag 12 and the PACF tails off at lags 12, 24, 36, …
  • Suggest and fit a model using sarima(). Check the residuals to ensure appropriate model fit.