Forecasting Financial Crises and Contagion in Asia
using Dynamic Factor Analysis
A. Cipollini* G. Kapetaniost
Essex University Queen Mary, University of London
May 25, 2008
Abstract
In this paper we use principal components analysis to obtain vulnerability indica-
tors able to predict financial turmoil. Probit modelling through principal components
and also stochastic simulation of a Dynamic Factor model are used to produce the cor-
responding probability forecasts regarding the currency crisis events affecting a number
of East Asian countries during the 1997-1998 period. The principal components model
improves upon a number of competing models, in terms of out-of-sample forecasting
performance.
Keywords: Financial Contagion, Dynamic Factor Model
JEL code: C32,C51,F34
1 Introduction
The currency and financial turmoil affecting the Latin American countries during the 1994
period and the East Asian emerging market economies during the 1997-1998 period has at-
tracted particular attention by both academics and policymakers. In particular, these crises
have fueled a new variety of theories, also known as third generation of currency crisis mod-
els, which focus on moral hazard and imperfect information. The emphasis is on excessive
booms and busts in international lending. In particular, throughout most of the 1990s, mas-
sive capital inflows had been pouring in the East Asian region, mainly in the form of bank
lending. Most of the foreign borrowing in these economies was short-term with Japan being
the country with the largest exposure. Therefore, the focus of this paper is to examine the
role played by the financial capital markets in propagating balance of payment crises across
Indonesia, Malaysia, Philippines, Korea, Thailand, during the 1997-1998 crisis period. Work
* Department of Accounting, Finance and Management, University of Essex, Wivenhoe Park, Colchester
C04 3SQ.
tDepartment of Economics, Queen Mary, University of London, Mile End Road, London E1 4NS. email:
[email protected]