Modeling fixed income excess returns

Excess returns earned in fixed-income markets have been modeled using the ARCH-M model of Engle et al. and its variants. We investigate whether the empirical evidence obtained from an ARCH-M type model is sensitive to the definition of the holding period (ranging from 5 days to 90 days) or to the choice of data used to compute excess returns (coupon or zero-coupon bonds). There is robust support for the inclusion of a term spread in a model of excess returns, while the significance of the in-mean term depends on characteristics of the underlying data.