Predicting the German Economy: Headline Survey Indices Under Test

Abstract

This analysis investigates the predictive power of the headline indices of the four most important German survey providers. We conduct an out-of-sample, real-time forecast experiment for growth of total and private sector gross domestic product and growth of gross value added in both the manufacturing and the service sector. All providers publish valuable leading indicators for both GDP measures, with some advantages for the ifo indicators and the Economic Sentiment Indicator, respectively. For the manufacturing sector, indicators provided by the ifo Institute are clearly superior. For the service sector, all indicators prove to have a similar nowcasting performance, whereas the Economic Sentiment Services of the Centre for European Research is preferable for one quarter-ahead predictions.

Quarterly GDP Estimates for the German States: New Data for Business Cycle Analyses and Long-Run Dynamics

“…The estimated output gaps strongly correlate with survey-based, demeaned capacity utilization measures introduced byLehmann et al (2022) for the German states. For the period from the second quarter 2011 to the fourth quarter of 2021, all correlation coefficients are greater or equal to 0.70.…”

“…In Germany, the ifo Institute Munich is the largest survey provider with the ifo Business Climate Germany as its most famous survey-based indicator. Next to the forecasting power of the ifo Business Climate Germany (Lehmann and Reif, 2021), the survey has proved to have high forecasting power in several dimensions (see, for a recent literature survey, Lehmann, 2022). So it does for the German states, for which the ifo Institute provides a large subset of its main indicators.…”

Forecasting regional industrial production with novel high‐frequency electricity consumption data

“…To this end, we aggregate the 15‐min‐interval electricity consumption data to the monthly frequency, making conventional forecasting models such as bridge equations applicable. To test the indicators' predictive power for Bavarian industrial production, we build upon Lehmann and Reif (2021) and apply the following five time series models (see Section B in the Supporting Information for more technical details): Benchmark model : AR(1) model with a constant and one lag of the target series. Indicator Model 1 : AR‐X(0,0) model with a constant and the contemporaneous value of an indicator but without lags of the target series. …”