We propose a new approach to forecasting the term structure of interest rates, which allows to efficiently extract the information contained in a large panel of yields. In particular, we use a large Bayesian Vector Autoregression (BVAR) with an optimal amount of shrinkage towards univariate AR models. Focusing on the U.S., we provide an extensive study on the forecasting performance of our proposed model relative to most of the existing alternative speci.cations. While most of the existing evidence focuses on statistical measures of forecast accuracy, we also evaluate the performance of the alternative forecasts when used within trading schemes or as a basis for portfolio allocation. We extensively check the robustness of our results via subsample analysis and via a data based Monte Carlo simulation. We .nd that: i) our proposed BVAR approach produces forecasts systematically more accurate than the random walk forecasts, though the gains are small; ii) some models beat the BVAR for a few selected maturities and forecast horizons, but they perform much worse than the BVAR in the remaining cases; iii) predictive gains with respect to the random walk have decreased over time; iv) di¤erent loss functions (i.e., "statistical" vs "economic") lead to di¤erent ranking of speci.c models; v) modelling time variation in term premia is important and useful for forecasting.
This paper argues in favour of a closer link between decision and forecast evaluation problems. Although the idea of using decision theory for forecast evaluation appears early in the dynamic stochastic programming literature, and has continued to be used in meteorological forecasts, it is hardly mentioned in standard academic textbooks on economic forecasting. Some of the main issues involved are illustrated in the context of a two-state, two-action decision problem as well as in a more general setting. Relationships between statistical and economic methods of forecast evaluation are discussed and useful links between Kuipers score, used as a measure of forecast accuracy in the meteorology literature, and the market timing tests used in finance, are established. An empirical application to the problem of stock market predictability is also provided, and the conditions under which such predictability could be exploited in the presence of transaction costs are discussed.