E-mail alert  |  Contact  
Search:       Go  
Background  |   Sponsoring institutions  |   Editorial board   |   Advisory board   |   Associate editors
Call for papers  |   Submission guidelines  |   Editorial process
Current issue  |   Past issues  |  
December issue
List of authors
 
Gruen, Plumb, Stone
Francis, Owyang, Theodorou
Allington, Kattuman, Waldmann
Boivin, Ng
Vega, Winkelried
Svensson, Tetlow
IJCB Home   Read the journal   Past issues
Past issues
2017
 
December
September
June
March
February
2016
 
December
September
June
March
2015
 
December
September
June
March
January
2014
 
December
September
June
March
2013
 
December
September
June
March
January
2012
 
December
September
June
March
January
2011
 
December
September
June
March
2010
 
December
September
June
March
2009
 
December
September
June
March
2008
 
December
September
June
March
2007
 
December
September
June
March
2006
 
December
September
June
March
2005
 
December
September
May

Understanding and Comparing Factor-Based Forecasts

Jean Boivin (Columbia University and NBER) and Serena Ng (University of Michigan)

Abstract

Forecasting using "diffusion indices" has received a good deal of attention in recent years. The idea is to use the common factors estimated from a large panel of data to help forecast the series of interest. This paper assesses the extent to which the forecasts are influenced by (i) how the factors are estimated and/or (ii) how the forecasts are formulated. We find that for simple data-generating processes and when the dynamic structure of the data is known, no one method stands out to be systematically good or bad. All five methods considered have rather similar properties, though some methods are better in long-horizon forecasts, especially when the number of time series observations is small. However, when the dynamic structure is unknown and for more complex dynamics and error structures such as the ones encountered in practice, one method stands out to have smaller forecast errors. This method forecasts the series of interest directly, rather than the common and idiosyncratic components separately, and it leaves the dynamics of the factors unspecified. By imposing fewer constraints, and having to estimate a smaller number of auxiliary parameters, the method appears to be less vulnerable to misspecification, leading to improved forecasts.

JEL Codes: E37, E47, C3, C53.

 
Full article (PDF, 35 pages 253 kb)