Recent empirical finance research has suggested the potential for series to exhibit non-linear adjustment to equilibrium. This paper examines a variety of such models and compares their performance with the linear alternative. Using short- and long-term UK interest rates we report evidence that a logistic smooth transition error-correction model is best able to characterize the data and to provide superior out-of-sample forecasts over both linear and non-linear alternatives. This model suggests that market dynamics differ depending on whether the deviations from longrun equilibrium are above or below the threshold value. Further, the logistic smooth transition model indicates that agents' actions imply quicker reversion to equilibrium when the long rate exceeds the short rate, and supports a central bank inflation targeting interpretation of the non-linearity.
|Number of pages
|Published - Sept 2004
- TRANSITION AUTOREGRESSIVE MODELS
- ECONOMIC TIME-SERIES
- ASYMMETRIC ADJUSTMENT