Catching a Floating Treasure: A Genuine Ex-Ante Forecasting Experiment in Real Time

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Terms of use: Documents in AbstractForecasting real economic activity poses a considerable challenge not only due to hard-to-predict events like the current financial crisis but also due to the fact that targeted variables often undergo significant revisions after their first publication. In this paper we report the results of a genuine ex-ante forecasting experiment in real time. It highlights the difficulties of hitting a moving target and shows that in a realistic setting linear models in combination with survey data perform as good as much more sophisticated approaches. JEL classification: E37, C35

Keeping a Finger on the Pulse of the Economy: Nowcasting Swiss GDP in Real-Time Squared

“…For Switzerland, Müller and Köberl (2012) provide a description of an ex ante real-time experiment in forecasting quarterly year-on-year GDP growth. The forecasting exercise of Müller and Köberl (2012) is an ongoing project that was started in the third quarter of 2007.…”

“…The forecasting exercise of Müller and Köberl (2012) is an ongoing project that was started in the third quarter of 2007. Since then a GDP growth forecast was issued every quarter and the authors committed themselves to released forecasts by making them publically available at the web and by means of electronic communication.…”

“…Since then a GDP growth forecast was issued every quarter and the authors committed themselves to released forecasts by making them publically available at the web and by means of electronic communication. 2 In this paper we describe a forecasting experiment that is similar in spirit to that of Müller and Köberl (2012). Nevertheless, it has a number of distinctive features concerning target variable, timing and frequency of release, and econometric approach.…”