Estimating the Common Output Cycle in Australia
Luke HartiganABSTRACT
Background/Objective
This study develops a statistical measure of Australia's common output cycle and investigates the extent to which cyclical fluctuations are shared across industries. It also evaluates whether the common output cycle provides useful information for forecasting inflation.
Methods
Frequency‐domain filtering is applied to industry‐level output to isolate its cyclical component. These cyclical components are then combined in a dynamic factor model featuring stochastic cycle dynamics to estimate the common output cycle.
Results
The estimated common output cycle has a period of around six years and reveals substantial heterogeneity across industries in the timing and strength of participation in the common cycle. Manufacturing and wholesale trade are closely synchronised with the common cycle, whereas agriculture and mining are predominantly driven by idiosyncratic cycles. The common output cycle's ability to forecast inflation is statistically indistinguishable from that of an AR(1) benchmark over the forecast horizons considered. There is also evidence of potential endpoint issues when estimating the common output cycle in real time.
Conclusion
The findings suggest that the common output cycle is best viewed as a descriptive measure of the historical features of the Australian output cycle that are shared across industries.
Implications/Significance
The results indicate that the common output cycle provides a useful summary of cross‐industry cyclical comovement, but offers limited additional predictive information for inflation beyond a simple autoregressive benchmark. Potential endpoint issues should also be considered when using the measure in real‐time applications.