Combination of theoretical models for exchange rate forecasting

Abstract

This paper states that there are exchange rate forecasting gains when combining in-sample data from different models based on economic theory. Data combination is performed using Bayesian model averaging (BMA). Using pooled data by group of countries (developed and emerging economies) generates accuracy gains in an important amount of cases, with respect to forecasts that use country information. Gains are larger for currencies of developed economies, but accuracy decreases as the forecast horizon is extended. BMA models for developed countries tend to be more “sparse” than emerging countries models

Keywords

• Bayesian Model Averaging, exchange rate, forecasting, model uncertainty.