Some Reflections on Trend-Cycle Decompositions with Correlated Components

This paper discusses a few interpretative issues arising from trend- cycle decompositions with correlated components. We determine the conditions under which correlated components may originate from: underestimation of the cyclical component; a cycle in growth rates, rather than in the levels; the hysteresis phenomenon; permanent- transitory decompositions, where the permanent component has richer dynamics than a pure random walk. Moreover, the consequences for smoothing and signal extraction are discussed: in particular, we establish that a negative correlation implies that future observations carry most of the information needed to assess cyclical stance. As a result, the components will be subject to high revisions. The overall conclusion is that the characterisation of economic fluctuations in macroeconomic time series largely remains an open issue.