The movements in oil prices are very complex and, therefore, seem to be unpredictable. However, one of the main challenges facing econometric models is to forecast such seemingly unpredictable economic series. Traditional linear structural models have not been promising when used for oil price forecasting. Although linear and nonlinear time series models have performed much better in forecasting oil prices, there is still room for improvement. If the data generating process is nonlinear, applying linear models could result in large forecast errors. Model specification in nonlinear modeling, however, can be very case dependent and time-consuming. In this paper, we model and forecast daily crude oil futures prices from 1983 to 2003, listed in NYMEX, applying ARIMA and GARCH models. We then test for chaos using embedding dimension, BDS(L), Lyapunov exponent, and neural networks tests. Finally, we set up a nonlinear and flexible ANN model to forecast the series. Since the test results indicate that crude oil futures prices follow a complex nonlinear dynamic process, we expect that the ANN model will improve forecasting accuracy. A comparison of the results of the forecasts among different models confirms that this is indeed the case.

No abstract

Many empirical studies on the oil price shock effects on the economies of oil-exporting countries have assumed a linear relationship between the shocks and macroeconomic variables, offering no insights on the dynamics of different types of shocks. The literature also assumes a homogeneous response to oil price shocks by oil-exporting countries. This paper investigates the non-linear effects of oil price shock on macroeconomic performance in the context of two groups of oil-exporting countries using a VAR model with price shocks estimated by a GARCH method. The model consists of oil price shocks and economic growth as two major variables of interest as well as intermediate variables such as investment, exchange rate, and inflation rate. The sample includes nine major oilexporting countries, six developing and three developed countries, for the period 1970-2010. The results indicate that not all oil-exporting countries are alike in responding to oil shocks. While oil shocks have asymmetric effects in oil-exporting developing countries; lower oil prices lead to major revenue cuts and ensuing stagnation in the economy, but higher oil prices and accompanying higher revenues do not translate into sustained economic growth; they do not have significant effect on economic growth in oil-exporting developed countries. The panel data estimation results also suggest that heterogeneous responses to oil price shocks in oil-exporting countries can be explained by differences in their institutional quality, particularly government effectiveness.

Arti®cial neural network modelling has recently attracted much attention as a new technique for estimation and forecasting in economics and ®nance. The chief advantages of this new approach are that such models can usually ®nd a solution for very complex problems, and that they are free from the assumption of linearity that is often adopted to make the traditional methods tractable. In this paper we compare the performance of BackPropagation Arti®cial Neural Network (BPN) models with the traditional econometric approaches to forecasting the in¯ation rate. Of the traditional econometric models we use a structural reduced-form model, an ARIMA model, a vector autoregressive model, and a Bayesian vector autoregression model. We compare each econometric model with a hybrid BPN model which uses the same set of variables. Dynamic forecasts are compared for three dierent horizons: one, three and twelve months ahead. Root mean squared errors and mean absolute errors are used to compare quality of forecasts. The results show the hybrid BPN models are able to forecast as well as all the traditional econometric methods, and to outperform them in some cases.

No abstract