Nonparametric Forecasting of the Manufacturing Output Growth with Firm-level Survey Data

Gérard Biau (), Olivier Biau () and Laurent Rouvière ()

Journal of Business Cycle Measurement and Analysis, 2008, vol. 2007, issue 3, 317-331

Abstract: A large majority of summary indicators derived from the individual responses to qualitative Business Tendency Surveys (which are mostly three-modality questions) result from standard aggregation and quantification methods. This is typically the case for the indicators called balances of opinion, which are currently used in short term analysis and considered by forecasters as explanatory variables in many models. In the present paper, we discuss a new statistical approach to forecast the manufacturing growth from firm-survey responses. We base our predictions on a forecasting algorithm inspired by the random forest regression method, which is known to enjoy good prediction properties. Our algorithm exploits the heterogeneity of the survey responses, works fast, is robust to noise and allows for the treatment of missing values. Starting from a real application on a French dataset related to the manufacturing sector, this procedure appears as a competitive method compared with traditional algorithms.

Keywords: Business Tendency Surveys; balance of opinion; short-term forecasting; manufactured production; k-nearest neighbor regression; random forecasts (search for similar items in EconPapers)
Date: 2008
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://doi.org/10.1787/jbcma-v2007-art15-en (text/html)
Full text available to READ online. PDF download available to OECD iLibrary subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:oec:stdkaa:5kzdnhzpzq8w

Access Statistics for this article

More articles in Journal of Business Cycle Measurement and Analysis from OECD Publishing, Centre for International Research on Economic Tendency Surveys Contact information at EDIRC.
Bibliographic data for series maintained by ().