We consider an extension of the fractionally integrated ARIMA(0, d, 0) model for quarterly UK inflation, where we allow the fractional integration parameter d to vary with the season s. This periodic ARFIMA(0, d, 0) model does not only provide an informative in-sample description, it may also be useful for out-of-sample forecasting. The main result is that the integration parameter in the first two quarters is significantly larger than that in the last two quarters.

, , ,
doi.org/10.1016/S0169-2070(96)00715-7, hdl.handle.net/1765/2104
International Journal of Forecasting
Erasmus School of Economics

Franses, P. H., & Ooms, M. (1997). A periodic long memory model for quarterly UK inflation. International Journal of Forecasting, 117–126. doi:10.1016/S0169-2070(96)00715-7