Professional Documents
Culture Documents
The Box-Jenkins Practical
The Box-Jenkins Practical
The Box-Jenkins Practical
The file ARIMA.wf1 contains quarterly data observations for the consumer price index (cpi) and gross
domestic product (gdp) of the UK economy. We shall try to identify the underlying ARMA model for
the gdp variable.
Step 1: As a first step we need to calculate the ACF and PACF of the raw data. To do this we need to
double-click on the gdp variable to open the variable in a new Eviews window. We can then calculate
the ACF and PACF and view their respective graphs by clicking on View/Correlogram in the window
that contains the gdp variable. This will give us Figure 13.3.
Step 2: We take logs and then first differences of the gdp series by typing the following commands
into the Eviews command line:
and then double-click on the newly created dlgdp (log-differenced series) and click again on
View/Correlogram to obtain the correlogram of the dlgdp series.
Step 3: From step 2 above we obtain the ACF and PACF of the dlgdp series, provided in Figure 13.4.
From this correlogram we can see that there are 2 to 3 spikes on the ACF, and then all are zero
quickly. This suggests that we might have up to MA(3) and AR(1) specifications. So, the possible
models are the ARIMA(1,0,3), ARIMA(1,0,2) or ARIMA(1,0,1) models.
Step 4: We then estimate the three possible models. The command for estimating the ARMA(1,0,3)
model is:
The results are presented in Tables 13.2, 13.3 and 13.4, respectively.
5% , 0.05**
Table 13.4:
Step 5: Finally, the diagnostics of the three alternative models need to be checked, to see which
model is the most appropriate. Summarized results of all three specifications are provided in Table
13.5, from which we see that in terms of the significance of estimated coefficients, the model that is
most appropriate is probably ARIMA(1,0,3). ARIMA(1,0,2) has two insignificant terms (the
coefficients of MA(1) and MA(2), but when we include MA(3), both are significant, the MA(3) term is
highly significant and the MA(2) term is significant at the 90% level. In terms of AIC and SBC , the
results are contradictory. AIC suggest model 1 whilst SBC suggest model 3. The adj-R 2 is higher for
model 3, followed by model 1. Remembering that we need a parsimonious model, there might be a
problem of overfitting here. For this we also check the Q-statistics of the correlograms of the
residuals for lags 8, 16 and 24. We see that only the ARIMA(1,0,3) model has insignificant lags for all
three cases, while the other two models have significant (for 90%) lags for the eighth and the 16 th
lag, suggesting that the residuals are serially correlated. So again, here the ARMA(1,0,3) model
seems to be the most appropriate. So evidence here suggests that the ARIMA(1,0,3) model is
probably the most appropriate one. We will therefore proceed with forecasting using this model.
Degrees of freedom = n - k
72 – 4 72 – 3 72 - 2
Final step – Forecasting, the last step is now to forecast. You can do so on the output of the chosen model. You
will need to first expand the sample range through double clicking on range then expand the sample with a year.
You can choose the option to forecast and remember to specify the period, in this case the period is from
1998Q3 to 1999Q2.
The forecasted values lie within two standard deviations as illustrated above.
You can also combine the forecasted period and the actual period as illustrated below:
Choose the forecasted variable and the actual variable and graph them together.