Early Warning Systems: A Survey and a Regime-switching Approach
Previous early-warning systems (EWSs) for currency crises have relied on models that require a priori dating of crises. This paper proposes an alternative EWS, based on a Markov-switching model, which identifies and characterizes crisis periods endogenously; this also allows the model to utilize information contained in exchange rate dynamics. The model is estimated using data for the period 1972-99 for the Asian crisis countries, taking a country-by-country approach. The model outperforms standard EWSs, both in signaling crises and reducing false alarms. Two lessons emerge. First, accounting for the dynamics of exchange rates is important. Second, different indicators matter for different countries, suggesting that the assumption of parameter constancy underlying panel estimates of EWSs may contribute to poor performance.
What people are saying - Write a review
We haven't found any reviews in the usual places.
A MarkovSwitching Approach to EarlyWarning Systems
1 other sections not shown
Other editions - View all
Alarm Signals Asian crisis assess average of exchange Berg and Pattillo binary crisis capital flows Caramazza Coeff contagion correctly called countries Crisis Dates Crisis Definition crisis episodes crisis index crisis periods crisis probability crisis variable crisis within 12 Currency Crises Currency Crises Study current account Dataset dependent variable devaluation early warning systems econometric Economic emerging markets exchange rate changes external factors false alarms Forecast Probabilities genetic algorithm Ghosh goodness-of-fit growth rate Indonesia interest rate changes International Monetary Fund Korea LIBOR likelihood likelihood-ratio test linear Literature on Currency macroeconomic Malaysia Markov Markov-switching model measures methodology monthly data months overfitting parameters performance Philippines predictive probit model rate and reserve real exchange rate real interest rate real overvaluation Recent Empirical Literature regime regression reserve changes sample short-term debt significant speculative attacks Speculative Pressure Episodes speculative pressure index survey T-stat Table Thailand threshold time-varying probabilities tranquil periods Weighted average