Forecasting the yield curve in a data-rich environment: a no-arbitrage factor-augmented VAR approach

摘要

This paper suggests a term structure model which parsimoniously exploits a broad macroeconomic information set. The model does not incorporate latent yield curve factors, but instead uses the common components of a large number of macroeconomic variables and the short rate as explanatory factors. Precisely, an affine term structure model with parameter restrictions implied by no-arbitrage is added to a Factor-Augmented Vector Autoregression (FAVAR). The model is found to strongly outperform different benchmark models in out-of-sample yield forecasts, reducing root mean squared forecast errors relative to the random walk up to 50% for short and around 20% for long maturities.