Predicting the direction of change in aggregate demand growth and its components

In this study, we set up a framework to generate the forecasts of growth in aggregate demand and its components using real-time data. In general, these forecasts (for 1983-2008) accurately predict directional change under symmetric loss and are thus of value to a user who assigns similar cost (loss) to incorrect upward and downward predictions. Our model is simple yet useful, especially to economically-rational agents who tend to balance the predictive benefit of a forecast against the cost of gathering and processing information. We conclude by suggesting that the success of our model may have to do with the stationary behavior of the series as well as monetary policy that aims to achieve sustainable growth with stable prices.