Determinantes de la tasa de cambio en Colombia: evaluación de pronósticos

This paper analyses the in sample forecasting performance of four models for the Colombian exchange rate during the period 1984:1-2004:1. The sticky price monetary (Dornbusch 1976),(Franke11979) and the Balassa-Samuelson (which gives a central role to the productivity differentials) approaches are used. Additionally, the Purchasing Power Parity condition (PPP) is analyzed. The forecasting ability of these models is compared using a random walk as a benchmark model. The measures used to evaluate the forecasts are the root mean square error (rms) and inequality coefficient of Theil. It is found that despite the great ability to predict, no model overcomes the random walk. This conclusion strengthens the previous results in the exchange rate determinants literature.