Title: Nowcasting real economic activity in the euro area: Assessing the impact of qualitative surveys
Authors: Raisa Basselier - National Bank of Belgium (Belgium) [presenting]
David de Antonio Liedo - National Bank of Belgium (Belgium)
Geert Langenus - National Bank of Belgium (Belgium)
Abstract: The contribution of survey data is analyzed, in particular various sentiment indicators, to nowcasts of quarterly euro area GDP. We transform the real-time dataflow into an interpretable flow of news, taking into account only the first data vintage based upon the original press releases. The news is defined in our particular example as the difference between the released values and the prediction of a mixed-frequency dynamic factor model. More concretely, we specify a number of factors that is large enough to synthesize all relevant information from the data. Our purpose is twofold. First, we aim to quantify the specific value added for nowcasting of a set of heterogeneous data releases including not only sentiment indicators constructed by Eurostat, Markit, the National Bank of Belgium, IFO, ZEW, GfK or Sentix, but also hard data regarding industrial production or retail sales in the euro area and in some of the largest euro area countries. Second, we provide a ranking of these indicators, taking into account their predictive character for GDP, as well as their timeliness. We do this on the basis of the Kalman filter gains. In general, hard data contribute less to the nowcasts: their relatively late availability implies that they can to a large extent be anticipated by nowcasting models and, hence, their news component is smaller. The prevalence of survey data remains also under the counterfactual that hard data is released timely without any delay.