Forecasting Bond Yields with Segmented Term Structure Models

Abstract

Inspired by the preferred-habitat theory, we propose parametric interest rate models that split the term structure into segments. The proposed models are compared to successful term structure benchmarks based on out-of-sample forecasting exercises using US Treasury data. We show that segmentation can improve long-horizon term structure forecasts when compared to non-segmentation. Additionally, introducing cointegration in latent factor dynamics of segmented models makes them particularly strong to forecast short-maturity yields. Better forecasting is justified by the segmented models' ability to accommodate idiosyncratic shocks in the cross-section of yields.