Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/60769 
Year of Publication: 
2008
Series/Report no.: 
Staff Report No. 327
Publisher: 
Federal Reserve Bank of New York, New York, NY
Abstract: 
We compare a number of data-rich prediction methods that are widely used in macroeconomic forecasting with a lesser known alternative: partial least squares (PLS) regression. In this method, linear, orthogonal combinations of a large number of predictor variables are constructed such that the covariance between a target variable and these common components is maximized. We show theoretically that when the data have a factor structure, PLS regression can be seen as an alternative way to approximate this unobserved factor structure. In addition, we prove that when a large data set has a weak factor structure, which possibly vanishes in the limit, PLS regression still provides asymptotically the best fit for the target variable of interest. Monte Carlo experiments confirm our theoretical results that PLS regression performs at least as well as principal components regression and rivals Bayesian regression when the data have a factor structure. But when the factor structure in the data is weak, PLS regression outperforms both principal components and Bayesian regressions. Finally, we apply PLS, principal components, and Bayesian regressions to a large panel of monthly U.S. macroeconomic data to forecast key variables across different subperiods. The results indicate that PLS regression usually has the best out-of-sample performance.
Subjects: 
Macroeconomic forecasting
factor models
forecast combination
principal components
partial least squares
Bayesian ridge regression
JEL: 
C22
C53
E37
E47
Document Type: 
Working Paper

Files in This Item:
File
Size
322.98 kB





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