Title: Going global: The role of international data in nowcasting German GDP
Authors: Philipp Hauber - Kiel Institute for the World Economy (Germany) [presenting]
Christian Schumacher - Deutsche Bundesbank (Germany)
Abstract: Factor models can summarize the co-movements of a large number of variables and have proven useful in nowcasting and short-term forecasting of GDP growth because they can tackle mixed-frequencies or missing observations at the current edge. The main aim is to assess the importance of international variables for nowcasting national developments, an issue, which - curiously - has received relatively little attention in the academic literature so far. Given the large number of variables at both the national and international level, the question arises whether all this information is useful for nowcasting or not. As such, we also contribute to the continuing debate on variable selection and the optimal size of factor models for forecasting. Rather than choosing variables ad-hoc, we employ sparse priors on the factor model's loadings for Bayesian estimation. Sparse priors can help to identify those business cycle indicators that essentially determine the factors, whereas irrelevant variables are sorted out. In an empirical exercise, we start nowcasting using a baseline factor model estimated on German GDP and a large number of monthly indicators for the German economy only. Then, we augment the national data by various indicators for the remaining G7 countries and compare the nowcast accuracy. Different model specifications are compared to identify the ones most suitable to extract useful predictive information for nowcasting in a large-data environment.