Example of Partial Autocorrelation

The manager of a shipping yard wants to study the amount of cargo that is transported. The manager uses the partial autocorrelation function to determine which terms to include in an ARIMA model.

  1. Open the sample data, Shipping.MTW.
  2. Choose Stat > Time Series > Partial Autocorrelation.
  3. In Series, enter Weight.
  4. Click OK.

Interpret the results

This graph shows that a significant correlation occurs at lag 1 and is followed by correlations that are not significant. This result indicates that the manager should include an autoregressive term or order 1 in the ARIMA model.