Inference in Expectations Models of the Term Structure: A Non-parametric Approach

Recent research has examined apparent deviations from the expectations theory of the term structure detectable in regression tests, which may be interpreted as efficiency tests. Efficiency is rejected in many studies. Inference is complicated, however, by the non-normality of regression residuals, invalidating standard parametric test procedures. The present paper examines these rejections using robust diagnostic methods and non-parametric tests. We find some evidence against the expectations theory of the term structure in U.S. data, but not in Canadian. We also investigate the possible explanation of a link between forecast error and the yield spread through models of time-variation in the liquidity premium.