CHANGES IN REGIME AND THE TERM STRUCTURE - A NOTE

In a recent paper in this journal, James Hamilton (1988) argues that anomalous behaviour of interest-rate data in the U.S. can be accommodated within the expectations model if allowance is made for the possibility of stochastic changes of regime. But close examination of his data reveals that an inappropriate series for the yield on ten-year bonds was used. With more appropriate data, his finding of a switch of regime over the period 1979-1982 appears to be robust. The stochastic regime-switching model, however, is no longer able to reconcile this data with the expectations model of the term structure. © 1992.