Year: 2010
Type: preprint
Abstract: Recent works in the econometric literature consider the problem of summarising efficiently a large set of variables and using this summary for a variety of purposes, including forecast (Stock and Watson, 2002;Forni et al., 2005;Giannone et al., 2008; for a wide review, see Eklund and Kapetanios, 2008).Factor analysis combined with linear modelling has been, usually, the main tool used for this objective.This paper presents a new statistical approach to forecast macro-economic aggregates, based on the Random Forests technique, originally developed as a learning classification tool (Breiman, 2001), which is known to enjoy good prediction properties and to be robust to noise.* Olivier Biau, seconded national expert from the INSEE -France, and Angela D'Elia are economic analysts in the
Authors: Olivier Biau, Angela D ́Elia
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W3128647842