Forecasting using a large number of predictors: is Bayesian regression a valid alternative to principal components?

Christine De Mol, Domenico Giannone and Lucrezia Reichlin

No 2006,32, Discussion Paper Series 1: Economic Studies from Deutsche Bundesbank

Abstract: This paper considers Bayesian regression with normal and doubleexponential priors as forecasting methods based on large panels of time series. We show that, empirically, these forecasts are highly correlated with principal component forecasts and that they perform equally well for a wide range of prior choices. Moreover, we study the asymptotic properties of the Bayesian regression under Gaussian prior under the assumption that data are quasi collinear to establish a criterion for setting parameters in a large cross-section.

Keywords: Bayesian VAR; ridge regression; Lasso regression; principal components; large cross-sections (search for similar items in EconPapers)
JEL-codes: C11 C13 C33 C53 (search for similar items in EconPapers)
Date: 2006
New Economics Papers: this item is included in nep-ets and nep-for
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (78)

Downloads: (external link)
https://www.econstor.eu/bitstream/10419/19661/1/200632dkp.pdf (application/pdf)

Related works:
Journal Article: Forecasting using a large number of predictors: Is Bayesian shrinkage a valid alternative to principal components? (2008)
Working Paper: Forecasting Using a Large Number of Predictors: Is Bayesian Regression a Valid Alternative to Principal Components? (2006)
Working Paper: Forecasting using a large number of predictors: Is Bayesian regression a valid alternative to principal components? (2006)
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:zbw:bubdp1:5040

Access Statistics for this paper

More papers in Discussion Paper Series 1: Economic Studies from Deutsche Bundesbank Contact information at EDIRC.
Bibliographic data for series maintained by ZBW - Leibniz Information Centre for Economics ().