Estimating Sectoral Cycles Using Cointegration and Common Features

This paper investigates the degree of short run and long run comovement in U.S. sectoral output data by estimating sectoral trends and cycles. A theoretical model based on Long and Plosser (1983) is used to derive a reduced form for sectoral output from first principles. Cointegration and common features (cycles) tests are performed and sectoral output data seem to share a relatively high number of common trends and a relatively low number of common cycles. A special trend-cycle decomposition of the data set is performed and the results indicate a very similar cyclical behavior across sectors and a very different behavior for trends. In a variance decomposition exercise, for prominent sectors such as Manufacturing and Wholesale/Retail Trade, the cyclical innovation is more important than the trend innovation.