Evaluating the Importance of PPP Error Correction in Exchange Rate Forecasting
This paper evaluates the effects of error correction based on purchasing power parity in exchange rate forecasting models. This is done by evaluating the performance of VAR, VEC and baseline univariate models using British and Dutch exchange rates towards Sweden for a wide range of forecasting horizons with a rolling window approach. Results are largely inconclusive, with no statistically significant difference in performance between the two main models of interest although mean performance largely mirror previous research, with error correction models tending towards relatively better performance for longer horizons, although these results seem sensitive to structural change and shocks to the underlying processes.
AT THIS PAGE YOU CAN DOWNLOAD THE WHOLE ESSAY. (follow the link to the next page)