A cyclical characterization of economic activity in the United States, 1887-1940

We analyze historical business cycles as a sum of short- and medium-term cycles defined for a particular class of unobserved component models. By associating the trend with the low frequencies of the pseudo-spectrum in the frequency domain, manipulation of the spectral bandwidth will allow us to define subjective trends with specific properties. In this paper, we show how these properties can be exploited to anticipate business cycle turning points, not only historically but also in a true ex-ante exercise. This procedure is applied to US pre-Second World War GNP quarterly data taking as reference the NBER and Romer’s business cycle datings.