A comprehensive examination is undertaken of Australian exchange rate data utilizing the ARCH family of models. Various econometric tests are performed in an attempt to identify the presence of ARCH effects in 21 daily Australian bilateral exchange rate series. Where appropriate, a number of ARCH models have been fitted and the results presented. Several issues are also addressed. The presence of asymmetry in the ARCH effects is tested, although little evidence is found of any such asymmetry, as well as criteria for selecting an optimal ARCH model from among those fitted. The ARCH effects present in less frequently sampled data are thought to diminish and this is tested for using a number of indicators. Finally, the impact is tested of modelling higher-order autocorrelation for the fitted ARCH models.
|Number of pages||18|
|Journal||Applied Financial Economics|
|Publication status||Published - 1997|