EconStor >
Deutsche Bundesbank, Forschungszentrum, Frankfurt am Main >
Discussion Paper Series 1: Economic Studies, Deutsche Bundesbank >

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10419/19661
  
Title:Forecasting using a large number of predictors: is Bayesian regression a valid alternative to principal components? PDF Logo
Authors:De Mol, Christine
Giannone, Domenico
Reichlin, Lucrezia
Issue Date:2006
Series/Report no.:Discussion paper Series 1 / Volkswirtschaftliches Forschungszentrum der Deutschen Bundesbank 2006,32
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.
Subjects:Bayesian VAR
ridge regression
Lasso regression
principal components
large cross-sections
JEL:C33
C13
C53
C11
Document Type:Working Paper
Appears in Collections:Discussion Paper Series 1: Economic Studies, Deutsche Bundesbank

Files in This Item:
File Description SizeFormat
200632dkp.pdf375.39 kBAdobe PDF
No. of Downloads: Counter Stats
Download bibliographical data as: BibTeX
Share on:http://hdl.handle.net/10419/19661

Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.