Please use this identifier to cite or link to this item: http://hdl.handle.net/10419/149477
Authors: 
Boot, Tom
Nibbering, Didier
Year of Publication: 
2016
Series/Report no.: 
Tinbergen Institute Discussion Paper 16-073/III
Abstract: 
Random subspace methods are a novel approach to obtain accurate forecasts in high-dimensional regression settings. We provide a theoretical justification of the use of random subspace methods and show their usefulness when forecasting monthly macroeconomic variables. We focus on two approaches. The first is random subset regression, where random subsets of predictors are used to construct a forecast. Second, we discuss random projection regression, where artificial predictors are formed by randomly weighting the original predictors. Using recent results from random matrix theory, we obtain a tight bound on the mean squared forecast error for both randomized methods. We identify settings in which one randomized method results in more precise forecasts than the other and than alternative regularization strategies, such as principal component regression, partial least squares, lasso, and ridge regression. The predictive accuracy on the high-dimensional macroeconomic FRED-MD data set increases substantially when using the randomized methods, with random subset regression outperforming any one of the above mentioned competing methods for at least 66\% of the series.
Subjects: 
dimension reduction
random projections
random subset regression
principal components analysis
forecasting
JEL: 
C32
C38
C53
C55
Document Type: 
Working Paper

Files in This Item:
File
Size
457.65 kB





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