Time-varying dependencies in exchange rate markets : a distributional approach
Finance Seminar by Julien Hambuckers (HEC Liège - 1701)
October 2018, Wednesday 3 (1:00 pm)
In this paper, we take a new look at the relationship between interest rate differentials and exchange rates.
To do so, we introduce a forecasting approach that accounts for high-order dependencies in daily exchange rates.
Our model relies on a GARCH-in-mean specification where the innovations are assumed to follow a sinh-arcsinh (SH)
ditribution with a time-varying asymmetry parameter, depending on interest rates. This model is used to predict the direction of change of three major currency pairs (USD/EUR, USD/GBP and USD/CHF) over the period 1999-2016. We find a dynamic asymmetry specification to be significant and driven by the interest rates. Economically speaking, we show that, notwithstanding a better in-sample performance compared to benchmark models for all pairs, we are able to obtain a positive out-of-sample performance for the USD/CHF pair.