Testing for seasonal unit roots by frequency domain regression
2005-08-12T14:45:12Z (GMT) by
This paper considers statistics based on spectral regression estimators for testing for seasonal unit roots in a time series. An advantage of the frequency domain approach is that it enables serial correlation to be treated nonparametrically, thereby facilitating an explicit focus on the frequencies at which unit roots are of interest. The limiting distributions of the proposed test statistics are derived and their size and power properties are explored in simulation experiments.