An analysis of daily volatility in the Japanese foreign exchange market

We assess the behavior of daily changes in the Japanese foreign exchange market within the framework of conditional volatility and the day of the week effects. Generalized autoregressive conditional heteroscedasticity (GARCH) model is applied to let exchange rate variances change through time with detection of heteroscedastic errors in the model. Empirical results verify that volatility of the Japanese foreign exchange market is persistent, which is compared with other developed countries for the corresponding period. Moreover, the day of the week effects are present in US dollar and British pound return series for the period January 1, 1999 to July 29, 2004. Seasonality of exchange rates in Japan foreign exchange markets may be exploitable and judged as evidence against informational efficiency of markets. Central bank intervention and interest rates are as potential sources of heteroscedastic errors in the foreign exchange rates.