A steady-state approach to trend/cycle decomposition of regime-switching processes

In this paper, we present a new approach to trend/cycle decomposition under the assumption that the trend is the permanent component and the cycle is the transitory component of an integrated time series. The permanent component is defined as the steady-state level of the series, a definition that has exploitable forecasting implications useful for identification. We operationalize the steady-state approach for regime-switching processes and we use generated data from such processes to demonstrate the advantages of the steady-state approach over alternative approaches to trend/cycle decomposition. We then apply the steady-state approach to estimate the trend and cycle of U.S. real GDP implied by a regime-switching forecasting model. Our findings portray a very different picture of the business cycle than implied by more traditional methods.