Testing for nonlinearity of exchange rates: an information-theoretic approach

Using a discrete parametric modeling approach, an efficient test statistic was computed for non-linearity in terms of variance of the residuals of the linear and nonlinear auto-regressive models by Akaike Information Criterion, and a surrogate data analysis was conducted. Findings – It shows that a nonlinear auto-regressive model outperforms a linear stochastic model in certain sub-samples of baht, pound, ringgit, and yen dollar exchange rates. However, when the test statistics using different model orders and the data for the entire samples are estimated, it appears that the nonlinear model has a better performance than the linear model in fitting Thai and Malaysian currencies. The nonlinear model performs better than the linear model in the case of the UK pound in two thirds of the models, but the linear models completely outperform the nonlinear models for the yen data.

Nonlinear, Exchange rates, Surrogate data, Exponential autoregressive model, Contagion, Information theory