Purchase - $30.00

How to Evaluate an Early-Warning System: Toward a Unified Statistical Framework for Assessing Financial Crises Forecasting Methods

39 Pages Posted: 14 Mar 2012  

Bertrand Candelon

University of Maastricht - Department of Economics

Elena-Ivona Dumitrescu

affiliation not provided to SSRN

Christophe Hurlin

University of Orleans

Date Written: April 2012

Abstract

This paper proposes an original and unified toolbox to evaluate financial crisis early-warning systems (EWS). It presents four main advantages. First, it is a model free method which can be used to assess the forecasts issued from different EWS (probit, logit, Markov switching models, or combinations of models). Second, this toolbox can be applied to any type of crisis EWS (currency, banking, sovereign debt, and so on). Third, it does not only provide various criteria to evaluate the (absolute) validity of EWS forecasts but also proposes some tests to compare the relative performance of alternative EWS. Fourth, this toolbox can be used to evaluate both in-sample and out-of-sample forecasts. Applied to a logit model for 12 emerging countries we show that the yield spread is a key variable for predicting currency crises exclusively for South-Asian countries. Besides, the optimal cut-off correctly allows us to identify now on average more than 2/3 of the crisis and calm periods.

Suggested Citation

Candelon, Bertrand and Dumitrescu, Elena-Ivona and Hurlin, Christophe, How to Evaluate an Early-Warning System: Toward a Unified Statistical Framework for Assessing Financial Crises Forecasting Methods (April 2012). IMF Economic Review, Vol. 60, Issue 1, pp. 75-113, 2012. Available at SSRN: https://ssrn.com/abstract=2021703 or http://dx.doi.org/10.1057/imfer.2012.4

Bertrand Candelon (Contact Author)

University of Maastricht - Department of Economics ( email )

P.O. Box 616
Maastricht, 6200 MD
Netherlands

Elena-Ivona Dumitrescu

affiliation not provided to SSRN

No Address Available

Christophe Hurlin

University of Orleans ( email )

Université d'Orléans
Rue de Blois B.P. 6739 45
France

Paper statistics

Downloads
0
Abstract Views
1,045