Prediction of quantiles by statistical learning and application to GDP forecasting - Archive ouverte HAL Access content directly
Conference Papers Year : 2012

Prediction of quantiles by statistical learning and application to GDP forecasting

(1, 2) , (3)
1
2
3

Abstract

In this paper, we tackle the problem of prediction and confidence intervals for time series using a statistical learning approach and quantile loss functions. In a first time, we show that the Gibbs estimator (also known as Exponentially Weighted aggregate) is able to predict as well as the best predictor in a given family for a wide set of loss functions. In particular, using the quantile loss function of Koenker and Bassett (1978), this allows to build confidence intervals. We apply these results to the problem of prediction and confidence regions for the French Gross Domestic Product (GDP) growth, with promising results.
Fichier principal
Vignette du fichier
quantile6.pdf (643.47 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00671982 , version 1 (20-02-2012)
hal-00671982 , version 2 (20-02-2012)
hal-00671982 , version 3 (06-08-2012)

Identifiers

Cite

Pierre Alquier, Xiaoyin Li. Prediction of quantiles by statistical learning and application to GDP forecasting. The Fifteenth International Conference on Discovery Science (DS 2012), Oct 2012, Lyon, France. pp.22-36. ⟨hal-00671982v3⟩
866 View
496 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More