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

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, whi...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Biau, Gérard (VerfasserIn)
Weitere Verfasser: Biau, Olivier (MitwirkendeR), Rouvière, Laurent (MitwirkendeR)
Format: Elektronisch Buchkapitel
Sprache:English
Veröffentlicht: Paris OECD Publishing 2008
Schlagworte:
Economics
Online-Zugang:DE-384
DE-473
DE-824
DE-29
DE-739
DE-355
DE-20
DE-1028
DE-1049
DE-521
DE-861
DE-898
DE-92
DE-91
DE-573
DE-19
Volltext
Zusammenfassung: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
Beschreibung:1 Online-Ressource (15 Seiten) 16 x 23cm
DOI:10.1787/jbcma-v2007-art15-en

Es ist kein Print-Exemplar vorhanden.

Fernleihe Bestellen Achtung: Nicht im THWS-Bestand! Volltext öffnen

Ähnliche Einträge