The nonlinear dynamic relationship of exchange rates: Parametric and nonparametric causality testing

Abstract

The present study investigates the long-term linear and nonlinear causal linkages among six currencies, namely EUR/USD, GBP/USD, USD/JPY, USD/CHF, AUD/USD and USD/CAD. The prime motivation for choosing these exchange rates comes from the fact that they are the most liquid and widely traded, covering about 90% of total FX trading worldwide. The data spans two periods (PI: 3/20/1991 -3/20/1997, PII: 3/20/2003 -3/20/2007) before and after the structural break of the Asian financial crisis, which set a platform for departure for causality testing. We apply a new nonparametric test for Granger non-causality by Diks and Panchenko (2005, 2006) as well as the conventional linear Granger test on the return time series. To ensure that any causality is strictly nonlinear in nature, we also examine the nonlinear causal relationships of pairwise VAR filtered residuals as well as in a six-variate formulation. We find remaining significant biand uni-directional causal nonlinear relationships in the return series. Finally, we investigate the hypothesis of nonlinear non-causality after controlling for conditional heteroskedasticity in the data using a GARCH-BEKK model. Our approach allows the entire variance-covariance structure of the currency interrelationship to be incorporated in order to explicitly capture the volatility spillover mechanism. Whilst the nonparametric test statistics are smaller in some cases, significant nonlinear causal linkages persisted even after GARCH filtering during both the pre-and post-Asian crisis period. This indicates that currency returns may exhibit asymmetries and statistically significant higher-order moments.JEL classification: C14; C51; F31

Stock market’s reaction to money supply: a nonparametric analysis

“…A similar approach has been proposed by Hiemstra and Jones (1994) who examined whether the Granger causality from volume to stock returns can be explained by volume serving as a proxy for information flow in the stochastic process generating stock return variance as suggested by Clark ' s (1973) latent common-factor model. Recently, Bekiros andDiks (2008) andDe Gooijer andSivarajasingham (2008) have also used the idea of controlling for conditional variance in order to reexamine the dynamic relationships between exchange rates and international stock markets, respectively. Bekiros and Diks (2008) found that the Granger causality between exchange rates persist after controlling for variance, whereas De Gooijer and Sivarajasingham (2008) found that the relationships between international stock markets disappear after filtering returns with multivariate GARCH models.…”

“…Recently, Bekiros andDiks (2008) andDe Gooijer andSivarajasingham (2008) have also used the idea of controlling for conditional variance in order to reexamine the dynamic relationships between exchange rates and international stock markets, respectively. Bekiros and Diks (2008) found that the Granger causality between exchange rates persist after controlling for variance, whereas De Gooijer and Sivarajasingham (2008) found that the relationships between international stock markets disappear after filtering returns with multivariate GARCH models.…”

Nonlinear spillovers between euro area sovereign bond markets

“…2 For the explanation of Granger causality test we follow Bekiros and Diks (2008) and Dajcman and Festić (2012).…”

Transfer Entropy for Nonparametric Granger Causality Detection: An Evaluation of Different Resampling Methods

“…In this case, we perform the Engle-Granger approach [45] first to eliminate the influence of the co-integration, and then perform the nonparametric test on the collected stationary residuals from the linear regression of ∆X t and ∆Y t on a constant and the co-integration term. The procedure is similar to that in [46].…”