For a fractional time series model integrated of order d we derive two results. First, it is obtained how a change in d affects the coefficients of the integration filter. For long memory (d0), the effect is always positive; in the case of anti-persistence (d0) the effect may be positive or...

Temporal aggregation is known to affect the persistence of time series. We study the aggregation of flow variables as well as stock data, and difference-stationarity is allowed for. Moreover, moving averages encountered when computing annual growth rates (seasonal differences) are investigated....

Following a general-to-specific modelling strategy, empirical economists sometimes delete variables with "wrong" signs from a regression equation. Such an elementary model selection step may affect subsequent inference. We determine the post-model-selection [PMS] effect analytically and numerically.

The European overnight rate (Eonia) signals the monetary policy stance of the European Central Bank. Controllability of the Eonia requires that the persistence of the spread between the Eonia and the key policy rate remains sufficiently low. We apply fractional integration techniques to examine...

The behavior of impulse response coefficients as persistence measures is discussed under fractional integration. Results for long memory processes are extended to the antipersistent case of short memory.