Page 306 - Special Topic Session (STS) - Volume 3

STS544 M. Camachoa et al.
1. Spain: real GDP, real wage income (RWI), electricity consumption (EC),
social security affiliation (SSA), registered unemployment (U), real credit
card spending deflated with the consumer price index (CCS), consumer
confidence (CC), industry confidence (IC), the slope of the yield curve
(10-year bond rate minus 3-month Euribor, SLOPE), the average
mortgage rate minus the 12-month Euribor (MR12E), the average
mortgage rate minus the 12-month Treasury bill rate (MR12TBR) and
real credit to the private sector (RCPS).
2. Eurozone: real GDP, unemployment (UR), industrial production (IP),
exports (Exp), Economic Sentiment Indicators for the euro area related
to industry (ESII), services (ESIS) and consumers (ESIC), total credit to
households (LHH) and term spread (beta)
3. US: real GDP, monthly industrial production (IPI), payroll employment
(EMPL), real personal income less transfers (RPI), and trade sales
(SALES), industrial new orders (MNO), housing starts (HOUSE), the
Conference Board consumer confidence index (CC) and the ISM
manufacturing PMI, SP500 and the term spread (SLOPE)
4. Argentina: real GDP, industrial production (IPI), quarterly employment
(EMPL), real personal income, and real trade sales (SALES) and
construction activity (ISAC).
5. World: GDP, industrial production (IPI), PMI, employment (EMPL),
exports orders (NExO) and the VIX.
The pseudo real-time forecasting accuracy of the models is examined in
Table 1, which shows the mean-squared forecast errors (MSE), as the average
of the deviations of the predictions from the final releases of GDP available in
the data set. Two alternative models are included in the forecast evaluation:
an autoregressive model of order two (AR) and a random walk (RW) model.
This table shows that the forecasts from DFM clearly outperform those from
univariate models.
Using our DFM, we have also investigated to what extent there has been
deviations between the official figures of GDP in Argentina and reliable
indicators of economic activity.

295 | I S I W S C 2 0 1 9