Within a New Zealand business cycle context, we assess whether Hamilton’s (H84) OLS
regression methodology produces stylised business cycle facts which are materially
different from HP1600 measures, and whether using the H84 predictor and other forecast
extensions improves the HP filter’s properties at the ends of series.
In general, H84 produces exaggerated volatilities and less credible trend movements
during key economic periods so there is no material advantage in using H84 de-trending
over HP1600. At the ends, the forecast-extended HP filter almost always performs better
than the HP filter with no extension which performs slightly better than H84 forecast
extension.