MODELLING AN EARLY WARNING SYSTEM FOR CURRENCY CRISES: A DYNAMIC PANEL PROBIT MODEL

Abstract

Purpose- The probability of currency crisis is attempted to be predicted by analysing the lagged binary crisis variable and some macroeconomic indicators.

Methodology- A new generation of early warning system model is developed in order to determine the leading indicators of the financial crises of 17 developing countries and the dynamic structure of the crises are examined by using the dynamic random effects probit model.

Findings- The results show that the 12th (C1t-12), 3rd(C1t-3), 2nd(C1t-2) and 1st (C1t-1) lags of the dependent variable have a statistically significant effect in explaining the probability of the currency crisis.

Conclusion- The results of the model show that true state dependence has a significant effect on the probability of currency crises in the short term. This clearly indicates that sources of endogenous persistence of crises should be taken into account in order to improve a new generation of EWS on the predictability of currency crisis.

Keywords

• Currency crises,dynamic panel probit models,early warning systems (EWS),developing countries,state dependence

References

1. Berg, A., & Borensztein, E., & Milesi-Ferretti G. M., & Pattillo, C. (1999). Anticipating balance of payment crises-the role early warning systems. IMF Occasional Papers, 186, 1-32.
2. Berg, A., & Pattillo, C. (1999). Predicting currency crises: The indicators approach and an alternative. Journal of International Money and Finance, 8, 561-586.
3. Bussiere, M., & Fratzscher, M. (2006). Towards a new early warning system of financial crises. Journal of International Money and Finance, 25(6), 953-973.
4. Bussiere M. (2007). Balance of payment crises in emerging markets how early were the “early” warning signals?. ECB Working Paper, 713, 1-41.
5. Candelon, B., & Dumitrescu, E. I., & Hurlin, C. (2014). Currency crises early warning systems: Why they should be dynamic. International Journal of Forecasting, 30(4), 1016-1029.
6. Dumitrescu, E. I. (2012). Econometric models for financial crises, Maastricht University, Dissertation, ISBN: 978 94 6159 152 4.
7. Eichengreen, B., & Rose, A. K., & Wyplosz, C. (1996). Contagious currency crises. NBER Working Paper Series, 1-48.
8. Falcetti, E., & Tudela, M. (2006). Modelling currency crises in emerging markets: A dynamic probit model with unobserved heterogeneity and autocorrelated errors. Oxford Bulletin of Economics and Statistics, 68(4), 445-471.

9. Frankel, J.A., & Rose, A. K. (1996). Currency crashes in emerging markets: an empirical treatment. International Finance Discussion Papers, 534, 1- 26.
10. Grotti, R., & Cutuli, G. (2018). Estimating dynamic random effects probit model with unobserved heterogeneity using stata. Retrieved from https://www.researchgate.net/publication/323524968_Estimating_dynamic_random_effects_probit_model_with_unobserved_heterogenei ty_ using_Stata
11. Heckman, J. J. (1981). Heterogeity and state dependence. National Bureau of Economic Research, 91-140.
12. Kaminsky, G., & Lizondo, S., & Reinhart, C. M. (1998). Leading indicators of currency crises. IMF Staff Papers, 45(1), 1-48.
13. Kaminsky, G. L., & Reinhart, C. M. (1999). The twin crises: The causes of banking and balance-of-payments problems. The American Economic Review, 89(3), 473-500.
14. Kumar, M., & Moorthy, U., & Perraudin, W. (2003). Predicting emerging market currency crashes. Journal of Empirical Finance, 427- 454.
15. Moreno, R., & Trehan, B. (2000). Common shocks and currency crises, Federal Reserve Bank of San Francisco, 1-41.
16. Rabe-Hesketh, S., & Skrondal, A. (2013). Avoiding biased versions of wooldridge’s simple solution to the initial conditions problem. Economics Letters, 120(2), 346-349.
17. Von Hagen, J., & Ho, T. (2003). Twin crises: A reexamination of empirical links. Center for European Integration Studies, Retrieved from https://www.gtap.agecon.purdue.edu/resources/download/1386.pdf.
18. Wooldridge, J. M. (2005). Simple solutions to the initial conditions problem in dynamic, nonlinear panel data model s with unobserved heterogeneity. Journal of Applied Econometrics, 20, 39-54.