A robust criterion for determining the number of static factors in approximate factor models

Lucia Alessi (), Matteo Barigozzi () and Marco Capasso ()
Additional contact information
Lucia Alessi: Laboratory of Economics and Management (LEM), Sant’Anna School of Advanced Studies, Piazza Martiri della Libertà, 33, 56127 Pisa, Italy., http://www.lem.sssup.it/

No 903, Working Paper Series from European Central Bank

Abstract: We propose a refinement of the criterion by Bai and Ng [2002] for determining the number of static factors in factor models with large datasets. It consists in multiplying the penalty function by a constant which tunes the penalizing power of the function itself as in the Hallin and Liška [2007] criterion for the number of dynamic factors. By iteratively evaluating the criterion for different values of this constant, we achieve more robust results than in the case of fixed penalty function. This is shown by means of Monte Carlo simulations on seven data generating processes, including heteroskedastic processes, on samples of different size. Two empirical applications are carried out on a macroeconomic and a financial dataset. JEL Classification: C52.

Keywords: Approximate factor models; Information criterion; Number of factors. (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-ecm
Date: Written 2008-05
View list of references

Downloads: (external link)
http://www.ecb.europa.eu/pub/pdf/scpwps/ecbwp903.pdf (application/pdf)

Related works:
Working Paper: A Robust Criterion for Determining the Number of Static Factors in Approximate Factor Models (2007)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Ordering information: This working paper can be ordered from
Press and Information Division, European Central Bank, Kaiserstrasse 29, 60311 Frankfurt am Main, Germany

Access Statistics for this paper

More papers in Working Paper Series from European Central Bank
Address: Postfach 16 03 19, Frankfurt am Main, Germany
Contact information at EDIRC.
Series data maintained by Official Publications ().