A Principal Components Approach to Cross-Section Dependence in Panels

provided by Research Papers in Economics

A Principal Components Approach to
Cross-Section Dependence in Panels

Jerry Coakley^α,b, Ana-Maria Fuertes^c, Ron Smith^b*
^aDepartment of Accounting, Finance and Management, University of Essex
b

Department of Economics, Birkbeck College, University of London
^cFaculty of Finance, City University Business School

First version: March 2001. This version: March 2002

Abstract

The use of GLS to deal with cross-section dependence in panels is
not feasible where N is large relative to T since the disturbance covari-
ance matrix is rank deficient. Neither is it the appropriate response
if the dependence results from omitted global variables or common
shocks correlated with the included regressors. These can be proxied
by the principal components of the residuals from a baseline regres-
sion. It is shown that the OLS estimates from a regression augmented
by these principal components are unbiased and consistent using se-
quential limits for large T, large N . Simulations show that this leads
to a substantial reduction in bias even for relatively small T and N
panels. An empirical application indicates that the impact of cross
section dependence seems to strengthen the case for long run PPP.
Keywords: Factor analysis; global shocks; omittted variable bias
JEL Classification: C32; F31

’Corresponding author: 7-15 Gresse St., London W1P 1PA, UK Tel: +44
207 6316413. Fax: +44 207 6316418. E-mail: [email protected].. Earlier
versions of this paper were presented at the 7th SCE International Conference on
Computing in Economics and Finance, Yale University, June 2001, and at seminars
at the Universities of Maastricht, Leeds and Swansea. We thank participants, Kit
Baum, Michael Binder, Bertrand Candelon and Martin Sola for helpful discussions.
Smith is grateful for support under ESRC grant L138251003.

1   2   3   4   >>

More intriguing information