IFOCAST: Methods of the Ifo short-term forecast
Kai Carstensen (),
Steffen Henzel (),
Johannes Mayr () and
ifo Schnelldienst, 2009, vol. 62, issue 23, 15-28
The assessment and forecast of the economic situation in the current and coming quarter is one of the key tasks of economic activity forecasting. The Ifo Institute bases its short-term forecasts of GDP on the three-stage IFOCAST approach. In the first stage, available monthly indicators, for example the Ifo Business Climate, are extrapolated and aggregated to a quarterly level. Special attention is given to industry production, which is updated with the aid of disaggregated Ifo survey data. In a second step the gross value added of individual economic sectors is predicted with the help of bridge equations. Using a combination approach, a number of models are joined in order to compensate for model insecurity. In a third step the quarterly forecasting of individual economic sectors is aggregated by means of the economic weights for the forecasting of GDP. Experience in both the forecasting literature and in practice shows that this approach supplies reliable short-term forecasts and is flexible enough to cope also with extreme developments. In addition to the multi-phased standard procedures, this article discusses the mixed-frequency models and boosting algorithms that complement the standard approach in the test phase.
JEL-codes: E30 (search for similar items in EconPapers)
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (37) Track citations by RSS feed
Downloads: (external link)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:ces:ifosdt:v:62:y:2009:i:23:p:15-28
Access Statistics for this article
ifo Schnelldienst is currently edited by Marga Jennewein
More articles in ifo Schnelldienst from ifo Institute - Leibniz Institute for Economic Research at the University of Munich Contact information at EDIRC.
Bibliographic data for series maintained by Klaus Wohlrabe ().