ABSTRACT
The distinction between long-run and short-term characteristics in time series has attracted much attention in the last two decades. Long-run characteristics in economic and financial data are usually associated with non-stationarity in time series and are called trends, whereas short-term fluctuations are stationary time series and are called cycles. Economic and financial time series can be viewed as combinations of these components of trends and cycles. Typically, a shock to a stationary time series would have an effect which would gradually disappear, leaving no permanent impact on the time series in the distant future, while a shock to a non-stationary time series would permanently change the path of the time series; or would permanently move the activity to a different level, either a higher or a lower level.
