Stylized facts of the business cycle revisited: A structural modelling approach

Stylized facts of the business cycle in the G7 countries are derived using a stochastic trend model, which allows for structural breaks in the underly ing series in various ways. The results are compared to those of Backus and Kehoe's paper (1992) which used the Hoderick-Prescott filter. Numerous stu dies have shown that this filter distorts the dynamic properties of the dat a, yielding misleading stylized facts. Boone and Hall (1999) developed a me thod to decompose time series based on the stochastic trend model that was demonstrated to be more reliable and robust in the presence of structural b reaks using Monte Carlo techniques. This paper applies this technique to gi ve new evidence on the smoothness of consumption, the counter-cyclicality o f prices and variability of investment and technological shocks in the I po st-war period. Copyright (C) 1999 John Wiley & Sons, Ltd.