ABSTRACT
The study investigates the effect of energy prices on exchange movement in the selected African countries using a monthly data of crude oil, coal, natural gas and aggregate prices and exchange rate from January 1980 to March 2018 are obtained from the International Financial Statistics (IFS) and World Bank Commodity Price data. This study uses a Nonlinear Auto regressive distributed lag (NARDL) developed by Shin et al. (2014) to show the asymmetric effect of energy prices on exchange rate and the model also show that there is a short run and long run relationship between the variables in the model by diving the energy prices into positive and negative changes.
The study further adopts the Westernlund and Narayan (2015) approach to check the predictability level of exchange rate using energy prices. It formulates whether the predictive mode on exchange rate forecasting performance matters. The evidence shows that energy prices are significant predictors of exchange rate in selected countries.
More also, the study shows that the predictors of the exchange rate exhibits persistence, conditional heteroscedasity, and endogeneity which have a hint on forecasting performance. Also, the forecast performance of both in-sample and out-of-sample performance show that there is a significant improvement in the asymmetric that is the asymmetric (WN_ASY) model is better in-sample and out-of-sample forecast than the conventional (WN) predictive model.
Conclusively, the study establishes that alternative model (AFRIMA) outperform the WN_ASY version in predicting exchange rate in the selected sub-Saharan Africa countries. Therefore, policy makers and professional should make policy towards curbing the negative effect of these other factors like price instability so as to reduce the risk of exposing the economy to negative energy prices and exchange rate which may affect standard on living, investment and revenue in that country.
ABSTRACT
The study investigates the effect of energy prices on exchange movement in the selected African countries using a monthly data of crude oil, coal, natural gas and aggregate prices and exchange rate from January 1980 to March 2018 are obtained from the International Financial Statistics (IFS) and World Bank Commodity Price data. This study uses a Nonlinear Auto regressive distributed lag (NARDL) developed by Shin et al. (2014) to show the asymmetric effect of energy prices on exchange rate and the model also show that there is a short run and long run relationship between the variables in the model by diving the energy prices into positive and negative changes.
The study further adopts the Westernlund and Narayan (2015) approach to check the predictability level of exchange rate using energy prices. It formulates whether the predictive mode on exchange rate forecasting performance matters. The evidence shows that energy prices are significant predictors of exchange rate in selected countries.
More also, the study shows that the predictors of the exchange rate exhibits persistence, conditional heteroscedasity, and endogeneity which have a hint on forecasting performance. Also, the forecast performance of both in-sample and out-of-sample performance show that there is a significant improvement in the asymmetric that is the asymmetric (WN_ASY) model is better in-sample and out-of-sample forecast than the conventional (WN) predictive model.
Conclusively, the study establishes that alternative model (AFRIMA) outperform the WN_ASY version in predicting exchange rate in the selected sub-Saharan Africa countries. Therefore, policy makers and professional should make policy towards curbing the negative effect of these other factors like price instability so as to reduce the risk of exposing the economy to negative energy prices and exchange rate which may affect standard on living, investment and revenue in that country.