This paper examines the business cycle properties of a small set of a
real US macroeconomic time series using a variety of detrending method
s. It is shown that both quantitatively and qualitatively 'stylized fa
cts' of US business cycles vary widely across detrending methods and t
hat alternative detrending filters extract different types of informat
ion from the data. Implications and suggestions for current macroecono
mic practice are provided. (C) 1998 Elsevier Science B.V. All rights r
eserved.