A value-at-risk analysis of carry trades using skew-GARCH models

Abstract

We carry out a value-at-risk (VaR) analysis of an extremely popular strategy in the currency markets, namely, "carry trades," whereby a position purchased in high interest rate currencies is funded by selling low interest rate currencies. Since the natural outcome of the truncated normal distribution of interest-rate spreads combined with the normal distribution of exchange rate returns is a skew-normal distribution, we consider a skew-normal innovation with zero mean for our analysis of carry trade returns using generalized autoregressive conditional heteroskedasticity (GARCH) models. The stress testing results reveal that skew-normal or densities are suitable for the measurement of VaR for carry trade returns involving, for example, taking up a long position in Australian Dollars or Argentine Peso which are funded by selling Japanese Yen.