A Three-State Early Warning System for the European Union

36 Pages Posted: 19 Oct 2018

See all articles by Savas Papadopoulos

Savas Papadopoulos

Democritus University of Thrace

Pantelis Stavroulias

affiliation not provided to SSRN

Thomas W. Sager

University of Texas at Austin - Red McCombs School of Business

Etti G. Baranoff

Virginia Commonwealth University (VCU) - Department of Finance, Insurance & Real Estate

Date Written: October 17, 2018

Abstract

The global financial crisis of 2007–8 focused the attention of the financial authorities on improving forecasting methods in order to avoid future financial crises of similar magnitude. We contribute to the literature on crisis prediction in several important ways. First, we develop an early warning system (EWS) that provides between seven and twelve quarters’ advance warning with high accuracy in out-of-sample testing. Second, our EWS applies region-wide to the leading economies in the European Union. Third, the methodology is transparent, utilizing only publicly available macrolevel data and comparing standard statistical classification methodology (multinomial logistic regression, discriminant analysis and neural networks). Fourth, we employ two relatively novel methodological innovations in EWS modeling: three-state (ternary) classification to guarantee a minimumadvance warning period, and a fitting and evaluation criterion (the total harmonic mean) that prioritizes avoiding classification errors for the relatively infrequent events of most interest. As a consequence, a policy maker who uses these methods will enjoy a high probability that future crises could be signaled well in advance and that crisis warnings will not be false alarms. Finally, since we focus on EU15, we provide an overall response on where the most common macroeconomic indicators can be used uniformly for that region.

Keywords: banking crisis, financial stability, macroprudential policy, classification methods, goodness-of-fit measures.

Suggested Citation

Papadopoulos, Savas and Stavroulias, Pantelis and Sager, Thomas W. and Baranoff, Etti G., A Three-State Early Warning System for the European Union (October 17, 2018). Journal of Risk, Vol. 21, No. 1, 2018, Available at SSRN: https://ssrn.com/abstract=3268100

Savas Papadopoulos (Contact Author)

Democritus University of Thrace ( email )

Dept. of International Economic Relations & Devel.
University Campus
Komitini, 69100
Greece
306977343023 (Phone)
302310340278 (Fax)

HOME PAGE: http://riskmetrica.wordpress.com/

Pantelis Stavroulias

affiliation not provided to SSRN

Thomas W. Sager

University of Texas at Austin - Red McCombs School of Business ( email )

Austin, TX 78712
United States

Etti G. Baranoff

Virginia Commonwealth University (VCU) - Department of Finance, Insurance & Real Estate ( email )

Richmond, VA 23284
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
0
Abstract Views
555
PlumX Metrics