Do Macroeconomic Variables Drive Exchange Rates Independently?

The classical practice in exchange rate model estimation is to use bilateral differentials of macro fundamentals. Empirically, capitals may not place equal importance on the economic fundamentals among all countries. Therefore, allowing each country’s variable to enter the model independently may reduce estimation error. Based on simulations, we find that higher correlation between the two countries’ variables leads to higher prediction error. Applying the Sticky Price Monetary Model (SPMM) to a wide range of countries with Elastic Net, a machine-learning based regression technique, we find supportive evidence for separating the variables, a finding especially relevant for smaller economies