Modelling the US real GNP with fractionally integrated techniques

The US real GNP is analysed by means of fractionally integrated techniques. LM tests proposed by Robinson for testing unit roots and other fractionally integrated hypotheses are applied to the quarterly GNP series and to its log-transformation. The maximum likelihood estimation procedure of Sowell for estimating ARFIMA models is implemented. The results indicate that the order of integration of the US real output is much higher than one, and thus, the standard approach of taking first differences may still produce series with long memory behaviour.