Theories, Techniques and the Formation of German Business Cycle Forecasts

Abstract

We report results of a survey among active forecasters of the German business cycle. Using data for 82 respondents from 37 different institutions, we investigate what models and theories forecasters subscribe to and find that they are pronounced conservative in the sense that they overwhelmingly rely on methods and theories that have been well-established for a long time, while more recent approaches are relatively unimportant for the practice of business cycle forecasting. DSGE models are mostly used in public institutions. In line with findings in the literature there are tendencies of “leaning towards consensus” (especially for public institutions) and “sticky adjustment of forecasts” with regard to new information. A stable relationship between preferred theories and methods and forecast accuracy cannot be established.

Combining Model‐Based Near‐Term GDP Forecasts and Judgmental Forecasts: A Real‐Time Exercise for the G7 Countries

“…This is consistent with the findings of the literature that forecasters adjust their forecast more frequently during recessions and banking crises (see for example Lundquist and Stekler, 2012;Loungani, Stekler and Tamirisa, 2013). Döpke et al (2017) report an increased awareness to evaluate forecast errors and methodologies on a regular basis after the crisis among forecasters of the German economy. Moreover, some forecasters seem to combine forecasts from different methods more often and try to minimize the dependency on one method.…”

“…Apart from the financial crisis episode, we thus find that Consensus forecasts only changed little in terms of updating, which is consistent with the finding in Döpke et al . () that forecasters did not fundamentally change their behaviour after the crisis. By contrast, DFM forecasts (and presumably those of other statistical models as well) did change substantially in this respect, especially at the F3 horizon when the available monthly information does not yet refer to the quarter to be forecasted.…”

“…Döpke et al . () report an increased awareness to evaluate forecast errors and methodologies on a regular basis after the crisis among forecasters of the German economy. Moreover, some forecasters seem to combine forecasts from different methods more often and try to minimize the dependency on one method.…”

“…This section investigates what benefits can be realistically expected from such a combination strategy in practice by simulating the forecasting procedure on the basis of real-time data. Forecast combinations are widely used by central banks and private sector forecasters (Aiolfi et al, 2011;Döpke et al, 2017). Our procedure consists of two steps.…”

“…By contrast, forecasts by professional analysts reflect much more information than statistical data, which are inevitably limited. Surveys among professional forecasters by European Central Bank (), Stark () and Döpke, Fritsche and Waldhof () indicate that GDP forecasts mostly reflect a mixture of model‐based and judgmental information. For example, 60% of the respondents in the European Central Bank () survey consider their short‐run forecasts as being model‐based but with judgmental adjustments, while 24% think they are essentially judgment‐based (experience and intuition) and 16% purely model‐based.…”