Temporal aggregation of stationary and nonstationary FARIMA (p, d, 0) models
We consider temporal aggregation of stationary and nonstationary time series with short memory, long memory and antipersistence, within the framework of fractional autoregressive processes. Asymptotically, long memory and antipersistence are preserved whereas short memory components vanish. In the case of integrated processes, the results extend Tiao's [15] to the fractional case.