We discuss representation of uncertainty in the business cycle clock. We propose approach utilising description of the unconditional mean of the process, applied for modelling dynamics of macroeconomic time series, as a trend component and almost period function in a non-parametric setting. We capture the dynamics over the business cycle, trend component and seasonal fluctuations and possible interactions between these features. A particular values of the almost periodic function are key for representation of the business cycle in a clock, expressing the dynamics according to phase diagram. The set of frequencies interpreted as a properties of the business fluctuations are invariant with respect to filtration methods applied in the procedure.
business cycle clock, filtration, almost periodically correlated processes
Abberger K., Nierhaus W., (2010), IFO Business Cycle Clock: Circular Correlation with the Real GDP, CESifo Working Paper Series No. 3179.
Gómez V., (1999), Three Equivalent Methods for Filtering Finite Nonstationary Time Series, Journal of Business and Economic Statistics, 17 (1), 109–117.
Gómez V., (2001), The Use of Butterworth Filters for Trend and Cycle Estimation in Economic Time Series, Journal of Business and Economic Statistics, 19 (3), 365–373.
Hodrick R., Prescott E., (1997), Postwar U.S. Business Cycles: An Empirical Investigation, Journal of Money, Credit and Banking, 29, 1–16.
Ladiray D., (2012), Theoretical and Real Trading-Day Frequencies, w: Bell W. R., Holan S. H., McErloy T. S., (red.), Economic Time Series: Modeling and Seasonality, 255–279.
Lenart Ł., Pipień M., (2013), Almost Periodically Correlated Time Series in Business Fluctuations Analysis, Acta Physica Polonica A, 123 (3), 567–583.
Lenart Ł., Mazur B., Pipień M., (2016), Statistical Analysis of Business Cycle Fluctuations in Poland Before and After the Crisis, Equilibrium. Quarterly Journal of Economics and Economic Policy (in press).
Luginbuhl R., de Vos A., (2003), Seasonality and Markov Switching in an Unobserved Component Time Series Model, Empirical Economics, 28, 365–386.