Can We Beat the Random-Walk Model for the South African Rand–U.S. Dollar and South African Rand–UK Pound Exchange Rates? Evidence from Dynamic Model Averaging

摘要: AbstractTraditionally, the literature on forecasting exchange rates with many potential predictors has primarily only accounted for parameter uncertainty using Bayesian model averaging (BMA). Although BMA-based models of tend to outperform random-walk model, we show that when accounting over and above through use dynamic (DMA) selection (DMS), gains relative are even bigger. That is, DMA DMS not but also BMA rates. Furthermore, sensitivity analysis reveals in exchange-rate modeling, may be more important than uncertainty. Our results based fifteen used forecast two South African rand–based We unveil variables, which vary time, good rand–dollar rand–pound...