Systemic Event Prediction by an Aggregate Early Warning System: An Application to the Czech Republic
Abstrakt
This work develops an early warning framework for assessing systemic risks and for predicting systemic events over the short horizon of six quarters and the long horizon of twelve quarters on the panel of 14 countries, both advanced and developing. First, we build Financial Stress Index to identify starting dates of systemic financial crises for each country in the panel.
Second, early warning indicators for assessment and prediction of systemic risk are selected in a two-step approach; we find relevant prediction horizons for each indicator by a univariate logit model followed by the application of Bayesian model averaging to identify the most useful indicators. Finally, we observe performance of the constructed EWS over both horizons on the Czech data and find that the model over the long horizon outperforms the EWS over the short horizon.
For both horizons, out-of-sample probability estimates do not deviate substantially from their in-sample estimates indicating a good out-of-sample performance for the Czech Republic.