Nonlinearities in Exchange rates: Double EGARCH Threshold Models for Forecasting Volatility

Sitzia, Bruno and Iovino, Doriana (2008): Nonlinearities in Exchange rates: Double EGARCH Threshold Models for Forecasting Volatility.

Abstract

This paper illustrates how to specify and test a Double Threshold EGARCH Model for some important exchange rates. The analysis is monthly and refers to the period 1990.01-2007.06. The procedure involves testing for Threshold effects the residuals of a linear autoregressive model of the exchange rate that is taken as the starting point. If this preliminary testing is favourable to the hypothesis off nonlinearity one then specifies and estimates a threshold model using Tong (1983,1990) algorithm, Tong algorithm allows to specify separately two AR regimes and helps locating both the delay and the parameters of the regimes using a search procedure based on the AIC. Residual for the SETAR model are then further tested for conditional heteroskedasticity. If it is present then a Double symmetric EGARCH is fitted to the data by maximum likelihood. The result is compared with an AR GARCH model both in sample and out of sample to asses whether there is any forecasting superiority of the more complex model. Reported results favour this outcome. In the text of the paper we report explicitly the results for the Japanese yen and the British pound exchange rates vis a vis the US dollar, but the same procedure has been applied to many other exchange rate series with results favourable to the double variance model in more than 50% of the cases. We report the complete results in the appendix. We conclude that the proposed model is both feasible and of wide applicability to the analysis of volatility of exchange rates. We add two provisos: data are monthly and the period of estimation reflects only the most recent experience.

• Item Type: MPRA Paper
• Language: English
• Keywords: non linearity; forecasting volatility; exchange rates
• Subjects: C - Mathematical and Quantitative Methods > C2 - Single Equation Models ; Single Variables > C22 - Time-Series Models ; Dynamic Quantile Regressions ; Dynamic Treatment Effect Models ; Diffusion Processes

References

BLAKE, A. P. and G. KAPETANIOS, “Testing For Arch In The Presence Of Nonlinearity Of Unknown Form In The Conditional Mean”, (2007) Journal of Forecasting, 137, 472-488.

BOERO, GIANNA and EMANUELA MARROCU, “The performance of Non-linear Exchange Rate Models: A Forecasting Comparison”, Journal of Forecasting 21,July 2002.

BROOKS, C. (2001), “A Double threshold GARCH Model for the French/Deutschmark Exchange Rate”, Journal of Forecasting, 20,135-143.

Li, C.W. and W.K. Li (1996),”On a Double Threshold Autoregressive Heteroscedastic Time Series Model”, Journal of Applied Econometrics, 11,3, pp.253-274.

LUMSDAINE, R.L and S.NG (1999), “Testing for ARCH in the Presence of a Possibly Misspecified Conditional Mean”, Journal of Econometrics 93(2).

LUUKKONEN, R., P. SAIKKONEN and T. TERÄSVIRTA (1988), “Testing linearity in univariate time series models”, Scandinavian Journal of Statistics, 15, 161-175.

LUUKKONEN, R., P. SAIKKONEN and T. TERÄSVIRTA (1988), “Testing linearity against smooth transition autoregressive models”; Biometrika, 75, 3, 491-499.

PIPPERNGER, MICHEL K. AND GREGORY G. GOERING, “Exchange rate Forecasting Results from a Threshold Autoregressive Model” Open Economies Review 9: 157-170 (1998)

POON, SER-HANG and CLIVE W. J. GRANGER, “Forecasting Volatility in Financial Markets: A Review”, Journal of Economic Literature, 41 (June 2003), pp. 478{539.

TONG, H. (1983), “Threshold models in nonlinear time series analysis”, New York, Springer-Verlag. TONG, H. (1990), “Nonlinear time Series, a dynamical system approach”; Oxford Statistical Science Series, 6, Claredon Press Oxford.

TSAY, R.S. (1986), “Nonlinearity tests for time series”, Biometrika,73, 2, 461-466.