Moving Endpoints and the Internal Consistency of Agents' Ex Ante Forecasts

Forecasts by rational agents contain embedded initial and terminal boundary conditions. Standard time series models generate two types of long-run boundary values or steady-state 'endpoints' – fixed endpoints and moving average endpoints. Neither can explain the shifting endpoints implied by postwar movements in the cross-section of forward rate forecasts in the term structure or by post-1979 changes in survey estimates of expected long-run inflation. Multiperiod forecasts by a broader class of 'moving endpoint' time series models provide substantially improved tracking of the historical term structure and generally support the internal consistency of the ex ante long-run expectations of bond traders and survey respondents.